Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.6507. Min Act: -0.1700
Data Index: 1045877 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.6195. Min Act: -0.1700
Data Index: 4316574 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.5257. Min Act: -0.1700
Data Index: 2622951 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.5882. Min Act: -0.1700
Data Index: 1910992 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.5882. Min Act: -0.1700
Data Index: 6582245 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.3695. Min Act: -0.1700
Data Index: 4762902 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.3070. Min Act: -0.1700
Data Index: 164154 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.3695. Min Act: -0.1700
Data Index: 5534867 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.3070. Min Act: -0.1700
Data Index: 5457319 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.2757. Min Act: -0.1700
Data Index: 4165397 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.2445. Min Act: -0.1700
Data Index: 2759388 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.2757. Min Act: -0.1700
Data Index: 8418739 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.2132. Min Act: -0.1700
Data Index: 6998143 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.2132. Min Act: -0.1700
Data Index: 7318055 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.2445. Min Act: -0.1700
Data Index: 7830680 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.2445. Min Act: -0.1700
Data Index: 8569917 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.2445. Min Act: -0.1700
Data Index: 4537803 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.2445. Min Act: -0.1700
Data Index: 1818051 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.2445. Min Act: -0.1700
Data Index: 3348480 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6507. Min Range: -7.6507
Max Act: 7.2757. Min Act: -0.1700
Data Index: 4436331 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19