Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.0532. Min Range: -12.0532
Max Act: 12.0532. Min Act: -0.1699
Data Index: 381233 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0532. Min Range: -12.0532
Max Act: 11.1157. Min Act: -0.1700
Data Index: 6098539 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0532. Min Range: -12.0532
Max Act: 11.0532. Min Act: -0.1700
Data Index: 3256022 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.8657. Min Act: -0.1700
Data Index: 900482 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.8032. Min Act: -0.1700
Data Index: 6187506 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.7407. Min Act: -0.1700
Data Index: 3812076 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.7407. Min Act: -0.1700
Data Index: 218993 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.7407. Min Act: -0.1700
Data Index: 1356220 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.7407. Min Act: -0.1700
Data Index: 5083687 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.6782. Min Act: -0.1700
Data Index: 7832850 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.6157. Min Act: -0.1700
Data Index: 625814 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.6782. Min Act: -0.1700
Data Index: 4021355 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.6157. Min Act: -0.1700
Data Index: 5850090 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.6782. Min Act: -0.1700
Data Index: 5001630 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.5532. Min Act: -0.1700
Data Index: 2282436 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.4907. Min Act: -0.1700
Data Index: 4726772 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.4907. Min Act: -0.1700
Data Index: 5154105 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.3657. Min Act: -0.1699
Data Index: 1009767 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.4282. Min Act: -0.1700
Data Index: 4144627 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0532. Min Range: -12.0532
Max Act: 10.4282. Min Act: -0.1700
Data Index: 3388882 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19