Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3810 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.4079. Min Act: -0.1700
Data Index: 7700494 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.3916. Min Act: -0.1700
Data Index: 8570572 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.3752. Min Act: -0.1700
Data Index: 2416683 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.3589. Min Act: -0.1700
Data Index: 550492 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.3752. Min Act: -0.1700
Data Index: 2230015 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.3261. Min Act: -0.1700
Data Index: 3694376 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.3425. Min Act: -0.1700
Data Index: 7095254 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.3425. Min Act: -0.1700
Data Index: 3520708 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.3096. Min Act: -0.1700
Data Index: 3997866 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.2932. Min Act: -0.1700
Data Index: 7882344 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.2767. Min Act: -0.1700
Data Index: 3506116 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.2767. Min Act: -0.1700
Data Index: 8363276 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.2437. Min Act: -0.1700
Data Index: 6198662 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.2602. Min Act: -0.1700
Data Index: 5490947 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.2437. Min Act: -0.1700
Data Index: 4142711 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.2437. Min Act: -0.1700
Data Index: 5780633 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.2272. Min Act: -0.1700
Data Index: 7306444 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.2437. Min Act: -0.1700
Data Index: 7368985 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.2272. Min Act: -0.1700
Data Index: 550490 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4079. Min Range: -2.4079
Max Act: 2.2106. Min Act: -0.1700
Data Index: 7606366 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19