Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1072 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.7936. Min Act: -0.1700
Data Index: 1802047 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.6061. Min Act: -0.1700
Data Index: 5474173 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.6374. Min Act: -0.1700
Data Index: 4759817 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.6061. Min Act: -0.1700
Data Index: 249283 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.6061. Min Act: -0.1700
Data Index: 1424330 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.5436. Min Act: -0.1700
Data Index: 7501084 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.5436. Min Act: -0.1700
Data Index: 4598518 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.5436. Min Act: -0.1700
Data Index: 160989 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.5124. Min Act: -0.1700
Data Index: 8147732 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.5124. Min Act: -0.1700
Data Index: 663498 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.5124. Min Act: -0.1700
Data Index: 8410169 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.5124. Min Act: -0.1700
Data Index: 586229 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.5124. Min Act: -0.1700
Data Index: 3492747 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.4811. Min Act: -0.1700
Data Index: 5454998 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.4811. Min Act: -0.1700
Data Index: 82224 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.4811. Min Act: -0.1700
Data Index: 1797826 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.4811. Min Act: -0.1700
Data Index: 7069630 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.4499. Min Act: -0.1700
Data Index: 3352834 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.4499. Min Act: -0.1700
Data Index: 1181498 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7936. Min Range: -4.7936
Max Act: 4.4499. Min Act: -0.1700
Data Index: 7415387 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19