Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.6506. Min Act: -0.1700
Data Index: 7082792 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.4944. Min Act: -0.1700
Data Index: 3027904 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.4631. Min Act: -0.1700
Data Index: 1022393 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.4319. Min Act: -0.1700
Data Index: 5492914 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3694. Min Act: -0.1700
Data Index: 2975205 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3694. Min Act: -0.1700
Data Index: 5653183 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3694. Min Act: -0.1700
Data Index: 5656811 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3381. Min Act: -0.1700
Data Index: 4764703 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3069. Min Act: -0.1700
Data Index: 5698376 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3381. Min Act: -0.1700
Data Index: 7621986 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3069. Min Act: -0.1700
Data Index: 8591180 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3069. Min Act: -0.1700
Data Index: 1612744 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3381. Min Act: -0.1700
Data Index: 3182325 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3069. Min Act: -0.1700
Data Index: 3216326 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.2756. Min Act: -0.1700
Data Index: 8382337 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.2756. Min Act: -0.1700
Data Index: 2576 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3069. Min Act: -0.1700
Data Index: 1918950 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.2756. Min Act: -0.1700
Data Index: 7326905 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.2756. Min Act: -0.1700
Data Index: 1468531 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.2444. Min Act: -0.1700
Data Index: 3162652 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19