Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8838. Min Range: -7.8838
Max Act: 7.8838. Min Act: -0.1700
Data Index: 8809405 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8838. Min Range: -7.8838
Max Act: 7.5088. Min Act: -0.1700
Data Index: 2019073 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8838. Min Range: -7.8838
Max Act: 7.2588. Min Act: -0.1700
Data Index: 8057454 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8838. Min Range: -7.8838
Max Act: 7.1963. Min Act: -0.1700
Data Index: 7603614 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8838. Min Range: -7.8838
Max Act: 7.1651. Min Act: -0.1700
Data Index: 7147024 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8838. Min Range: -7.8838
Max Act: 7.1026. Min Act: -0.1700
Data Index: 2613596 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8838. Min Range: -7.8838
Max Act: 7.1026. Min Act: -0.1700
Data Index: 7708512 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8838. Min Range: -7.8838
Max Act: 7.1026. Min Act: -0.1700
Data Index: 4742588 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8838. Min Range: -7.8838
Max Act: 7.0713. Min Act: -0.1700
Data Index: 5255901 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8838. Min Range: -7.8838
Max Act: 7.0401. Min Act: -0.1700
Data Index: 1093275 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8838. Min Range: -7.8838
Max Act: 7.0401. Min Act: -0.1700
Data Index: 4892221 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8838. Min Range: -7.8838
Max Act: 6.9776. Min Act: -0.1700
Data Index: 7418388 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8838. Min Range: -7.8838
Max Act: 6.9151. Min Act: -0.1700
Data Index: 2269832 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8838. Min Range: -7.8838
Max Act: 6.9776. Min Act: -0.1700
Data Index: 225994 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8838. Min Range: -7.8838
Max Act: 6.9776. Min Act: -0.1700
Data Index: 7973285 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8838. Min Range: -7.8838
Max Act: 6.8838. Min Act: -0.1700
Data Index: 3152357 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8838. Min Range: -7.8838
Max Act: 6.9463. Min Act: -0.1700
Data Index: 7416643 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8838. Min Range: -7.8838
Max Act: 6.8213. Min Act: -0.1700
Data Index: 5098253 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8838. Min Range: -7.8838
Max Act: 6.8526. Min Act: -0.1700
Data Index: 4809750 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8838. Min Range: -7.8838
Max Act: 6.8526. Min Act: -0.1700
Data Index: 7038590 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19