Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2850 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.8758. Min Act: -0.1700
Data Index: 8430700 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.9070. Min Act: -0.1700
Data Index: 8232707 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.8445. Min Act: -0.1700
Data Index: 3988112 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.8133. Min Act: -0.1700
Data Index: 231341 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.8133. Min Act: -0.1700
Data Index: 2754757 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.7820. Min Act: -0.1700
Data Index: 8100041 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.7820. Min Act: -0.1700
Data Index: 1154972 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.7508. Min Act: -0.1700
Data Index: 536035 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.7508. Min Act: -0.1700
Data Index: 5385531 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.6883. Min Act: -0.1700
Data Index: 5869976 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.7195. Min Act: -0.1700
Data Index: 2959408 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.7195. Min Act: -0.1700
Data Index: 457396 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.7195. Min Act: -0.1700
Data Index: 4328964 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.6570. Min Act: -0.1700
Data Index: 163455 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.6570. Min Act: -0.1700
Data Index: 2302133 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.7195. Min Act: -0.1700
Data Index: 3408880 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.6883. Min Act: -0.1700
Data Index: 5129967 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.6883. Min Act: -0.1700
Data Index: 3030207 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.6883. Min Act: -0.1700
Data Index: 3016495 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9070. Min Range: -4.9070
Max Act: 4.6883. Min Act: -0.1700
Data Index: 1995214 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19