Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1601 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.6883. Min Act: -0.1700
Data Index: 4327972 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.6570. Min Act: -0.1700
Data Index: 5543603 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.5008. Min Act: -0.1700
Data Index: 7385225 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.5008. Min Act: -0.1700
Data Index: 975874 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.5008. Min Act: -0.1700
Data Index: 2049932 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.4695. Min Act: -0.1700
Data Index: 6180978 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.4070. Min Act: -0.1700
Data Index: 757006 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.4070. Min Act: -0.1700
Data Index: 7937719 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.4383. Min Act: -0.1700
Data Index: 2096434 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.4695. Min Act: -0.1700
Data Index: 222399 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.4383. Min Act: -0.1700
Data Index: 5594695 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.4070. Min Act: -0.1700
Data Index: 7250318 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.3758. Min Act: -0.1700
Data Index: 2896305 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.3758. Min Act: -0.1700
Data Index: 5757999 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.3758. Min Act: -0.1700
Data Index: 270701 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.4070. Min Act: -0.1700
Data Index: 7994876 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.3133. Min Act: -0.1700
Data Index: 1865999 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.3758. Min Act: -0.1700
Data Index: 1483306 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.3133. Min Act: -0.1700
Data Index: 3630485 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6883. Min Range: -7.6883
Max Act: 7.3133. Min Act: -0.1700
Data Index: 3975377 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19