Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1020 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1396. Min Range: -8.1396
Max Act: 8.1396. Min Act: -0.1700
Data Index: 3597515 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1396. Min Range: -8.1396
Max Act: 7.1396. Min Act: -0.1700
Data Index: 7022808 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1396. Min Range: -8.1396
Max Act: 7.1083. Min Act: -0.1700
Data Index: 8364462 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1396. Min Range: -8.1396
Max Act: 7.0771. Min Act: -0.1700
Data Index: 7900217 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.9833. Min Act: -0.1700
Data Index: 2154135 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.9521. Min Act: -0.1700
Data Index: 1989232 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.9208. Min Act: -0.1700
Data Index: 7099601 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.9833. Min Act: -0.1700
Data Index: 1466908 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.9521. Min Act: -0.1700
Data Index: 3237209 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.9521. Min Act: -0.1700
Data Index: 4261529 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.9208. Min Act: -0.1700
Data Index: 7534508 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.9208. Min Act: -0.1700
Data Index: 3736227 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.9208. Min Act: -0.1700
Data Index: 3269837 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.8896. Min Act: -0.1700
Data Index: 856117 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.8896. Min Act: -0.1700
Data Index: 6614696 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.8583. Min Act: -0.1700
Data Index: 8245358 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.8583. Min Act: -0.1700
Data Index: 5896047 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.8271. Min Act: -0.1700
Data Index: 1341281 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.7958. Min Act: -0.1700
Data Index: 3333985 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1396. Min Range: -8.1396
Max Act: 6.7646. Min Act: -0.1700
Data Index: 1622252 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19