Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3767 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.8434. Min Act: -0.1700
Data Index: 4057241 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.5934. Min Act: -0.1700
Data Index: 2539423 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.5309. Min Act: -0.1700
Data Index: 339720 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.4996. Min Act: -0.1700
Data Index: 1357769 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.4684. Min Act: -0.1700
Data Index: 3685691 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.4684. Min Act: -0.1700
Data Index: 5810764 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.3434. Min Act: -0.1700
Data Index: 8716794 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.3121. Min Act: -0.1700
Data Index: 3186541 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.2809. Min Act: -0.1700
Data Index: 7787364 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.2809. Min Act: -0.1700
Data Index: 3046244 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.2496. Min Act: -0.1700
Data Index: 7199899 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.2184. Min Act: -0.1700
Data Index: 3170517 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.2184. Min Act: -0.1700
Data Index: 7821708 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.1871. Min Act: -0.1700
Data Index: 5617024 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.1871. Min Act: -0.1700
Data Index: 1995720 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.1871. Min Act: -0.1700
Data Index: 8300720 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.1559. Min Act: -0.1700
Data Index: 4374453 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.1559. Min Act: -0.1700
Data Index: 4800000 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.1559. Min Act: -0.1700
Data Index: 4472312 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8434. Min Range: -7.8434
Max Act: 7.1559. Min Act: -0.1700
Data Index: 4742327 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19