Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3362 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.5332. Min Act: -0.1700
Data Index: 3346151 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.4707. Min Act: -0.1700
Data Index: 5228471 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.4082. Min Act: -0.1700
Data Index: 1020656 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.3457. Min Act: -0.1700
Data Index: 1306670 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.2207. Min Act: -0.1700
Data Index: 8630976 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.1582. Min Act: -0.1700
Data Index: 5970867 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.1894. Min Act: -0.1700
Data Index: 702471 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.1269. Min Act: -0.1700
Data Index: 6511638 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.0957. Min Act: -0.1700
Data Index: 742062 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.0957. Min Act: -0.1700
Data Index: 2759381 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.0644. Min Act: -0.1700
Data Index: 3046376 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.0644. Min Act: -0.1700
Data Index: 1306665 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.0019. Min Act: -0.1700
Data Index: 3412599 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5332. Min Range: -7.5332
Max Act: 7.0019. Min Act: -0.1700
Data Index: 7083524 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5332. Min Range: -7.5332
Max Act: 6.8457. Min Act: -0.1700
Data Index: 6783904 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5332. Min Range: -7.5332
Max Act: 6.8457. Min Act: -0.1700
Data Index: 5558254 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5332. Min Range: -7.5332
Max Act: 6.8457. Min Act: -0.1700
Data Index: 4865079 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5332. Min Range: -7.5332
Max Act: 6.8457. Min Act: -0.1700
Data Index: 8822589 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5332. Min Range: -7.5332
Max Act: 6.8144. Min Act: -0.1700
Data Index: 4825750 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5332. Min Range: -7.5332
Max Act: 6.8144. Min Act: -0.1700
Data Index: 4471256 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19