Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2497 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2897. Min Range: -4.2897
Max Act: 4.2897. Min Act: -0.1700
Data Index: 8812578 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2897. Min Range: -4.2897
Max Act: 4.2272. Min Act: -0.1700
Data Index: 2604016 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2897. Min Range: -4.2897
Max Act: 4.1647. Min Act: -0.1700
Data Index: 4721502 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2897. Min Range: -4.2897
Max Act: 4.1335. Min Act: -0.1700
Data Index: 4177541 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2897. Min Range: -4.2897
Max Act: 4.1335. Min Act: -0.1700
Data Index: 4628112 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2897. Min Range: -4.2897
Max Act: 4.1335. Min Act: -0.1700
Data Index: 8817887 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2897. Min Range: -4.2897
Max Act: 4.1022. Min Act: -0.1700
Data Index: 1220577 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2897. Min Range: -4.2897
Max Act: 4.0397. Min Act: -0.1700
Data Index: 4628113 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.9772. Min Act: -0.1700
Data Index: 6463067 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.9772. Min Act: -0.1700
Data Index: 5855345 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.9772. Min Act: -0.1700
Data Index: 3617052 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.9772. Min Act: -0.1700
Data Index: 7013227 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.9146. Min Act: -0.1700
Data Index: 276910 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.9146. Min Act: -0.1700
Data Index: 693292 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.9146. Min Act: -0.1700
Data Index: 1772316 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.9146. Min Act: -0.1700
Data Index: 5153648 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.8834. Min Act: -0.1700
Data Index: 6512652 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.8834. Min Act: -0.1700
Data Index: 4773955 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.8521. Min Act: -0.1700
Data Index: 6715206 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2897. Min Range: -4.2897
Max Act: 3.8208. Min Act: -0.1700
Data Index: 5606569 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19