Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.4631. Min Act: -0.1700
Data Index: 8710573 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.3381. Min Act: -0.1700
Data Index: 5028893 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.3068. Min Act: -0.1700
Data Index: 6154138 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.2443. Min Act: -0.1700
Data Index: 697128 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.2131. Min Act: -0.1700
Data Index: 4334284 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.2131. Min Act: -0.1700
Data Index: 1904449 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.1506. Min Act: -0.1700
Data Index: 7599247 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.1506. Min Act: -0.1700
Data Index: 987627 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.1506. Min Act: -0.1700
Data Index: 6308710 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.1506. Min Act: -0.1700
Data Index: 4981986 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.0881. Min Act: -0.1700
Data Index: 3401253 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.0881. Min Act: -0.1700
Data Index: 1809546 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.0881. Min Act: -0.1700
Data Index: 4873395 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.0568. Min Act: -0.1700
Data Index: 4257227 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.0255. Min Act: -0.1700
Data Index: 3478786 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.0568. Min Act: -0.1700
Data Index: 6623120 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.0568. Min Act: -0.1700
Data Index: 6850091 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4631. Min Range: -4.4631
Max Act: 4.0255. Min Act: -0.1700
Data Index: 3058516 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4631. Min Range: -4.4631
Max Act: 3.9943. Min Act: -0.1700
Data Index: 5129682 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4631. Min Range: -4.4631
Max Act: 3.9943. Min Act: -0.1700
Data Index: 162582 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19