Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1259 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.5333. Min Act: -0.1700
Data Index: 669356 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.4708. Min Act: -0.1700
Data Index: 402127 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.4396. Min Act: -0.1700
Data Index: 1462113 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.4083. Min Act: -0.1700
Data Index: 5312385 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.4083. Min Act: -0.1700
Data Index: 6055079 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.3771. Min Act: -0.1700
Data Index: 6623045 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.3458. Min Act: -0.1700
Data Index: 1840933 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.2833. Min Act: -0.1700
Data Index: 1872430 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.2833. Min Act: -0.1700
Data Index: 177672 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.2521. Min Act: -0.1700
Data Index: 3505515 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.1896. Min Act: -0.1700
Data Index: 2043928 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.2208. Min Act: -0.1700
Data Index: 115763 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.2208. Min Act: -0.1700
Data Index: 260988 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.2208. Min Act: -0.1700
Data Index: 8056275 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.1896. Min Act: -0.1700
Data Index: 418247 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.1583. Min Act: -0.1700
Data Index: 7076846 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.1271. Min Act: -0.1700
Data Index: 4348210 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.1583. Min Act: -0.1700
Data Index: 5946793 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.1583. Min Act: -0.1700
Data Index: 1940591 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5333. Min Range: -6.5333
Max Act: 6.1271. Min Act: -0.1700
Data Index: 2440696 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19