Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2195 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0409. Min Range: -6.0409
Max Act: 6.0409. Min Act: -0.1700
Data Index: 2296707 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.9472. Min Act: -0.1700
Data Index: 2296696 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.9159. Min Act: -0.1700
Data Index: 4708294 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.9159. Min Act: -0.1700
Data Index: 634244 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.9159. Min Act: -0.1700
Data Index: 7690144 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.8222. Min Act: -0.1700
Data Index: 3296501 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.7909. Min Act: -0.1700
Data Index: 2854814 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.7284. Min Act: -0.1700
Data Index: 6112230 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.7284. Min Act: -0.1700
Data Index: 8765342 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.6347. Min Act: -0.1700
Data Index: 6249104 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.6347. Min Act: -0.1700
Data Index: 2390622 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.6347. Min Act: -0.1700
Data Index: 7165406 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.6347. Min Act: -0.1700
Data Index: 90432 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.6347. Min Act: -0.1700
Data Index: 6958836 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.6347. Min Act: -0.1700
Data Index: 6670452 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.6347. Min Act: -0.1700
Data Index: 6249090 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.5722. Min Act: -0.1700
Data Index: 5073567 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.6034. Min Act: -0.1700
Data Index: 4075379 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.6034. Min Act: -0.1700
Data Index: 6950322 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0409. Min Range: -6.0409
Max Act: 5.6034. Min Act: -0.1700
Data Index: 8560250 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19