Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2605 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.8272. Min Act: -0.1700
Data Index: 1326449 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.6084. Min Act: -0.1700
Data Index: 4794083 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.3272. Min Act: -0.1700
Data Index: 768566 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.2959. Min Act: -0.1700
Data Index: 4713683 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.2959. Min Act: -0.1700
Data Index: 3441223 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.2334. Min Act: -0.1700
Data Index: 2641634 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.2022. Min Act: -0.1700
Data Index: 4242862 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.2022. Min Act: -0.1700
Data Index: 39288 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1709. Min Act: -0.1700
Data Index: 3002050 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1709. Min Act: -0.1700
Data Index: 3126731 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1709. Min Act: -0.1700
Data Index: 3447814 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1397. Min Act: -0.1700
Data Index: 1931968 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1709. Min Act: -0.1700
Data Index: 40438 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1397. Min Act: -0.1700
Data Index: 7862538 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1397. Min Act: -0.1700
Data Index: 5587494 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1397. Min Act: -0.1700
Data Index: 1909072 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1397. Min Act: -0.1700
Data Index: 2716429 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1084. Min Act: -0.1700
Data Index: 4761782 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1084. Min Act: -0.1700
Data Index: 5073609 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8272. Min Range: -5.8272
Max Act: 5.1084. Min Act: -0.1700
Data Index: 1208396 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19