Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.9957. Min Act: -0.1700
Data Index: 3337562 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.8082. Min Act: -0.1700
Data Index: 10326 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.7457. Min Act: -0.1700
Data Index: 8280689 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.6832. Min Act: -0.1700
Data Index: 6113058 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.6207. Min Act: -0.1700
Data Index: 3451905 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.5582. Min Act: -0.1700
Data Index: 7544797 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.4957. Min Act: -0.1700
Data Index: 303694 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.4957. Min Act: -0.1700
Data Index: 522340 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.4957. Min Act: -0.1700
Data Index: 2070993 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.4332. Min Act: -0.1700
Data Index: 4296644 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.3707. Min Act: -0.1700
Data Index: 4022320 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.3082. Min Act: -0.1700
Data Index: 4899756 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.3707. Min Act: -0.1700
Data Index: 1425117 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.3707. Min Act: -0.1700
Data Index: 7760159 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.3707. Min Act: -0.1700
Data Index: 4078954 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.3707. Min Act: -0.1700
Data Index: 7544796 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.3707. Min Act: -0.1700
Data Index: 2244287 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.3082. Min Act: -0.1700
Data Index: 642524 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.3082. Min Act: -0.1700
Data Index: 1667722 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9957. Min Range: -8.9957
Max Act: 8.3082. Min Act: -0.1700
Data Index: 358132 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19