Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.3411. Min Act: -0.1700
Data Index: 1434283 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.2786. Min Act: -0.1700
Data Index: 1545768 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.2786. Min Act: -0.1700
Data Index: 636570 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.2474. Min Act: -0.1700
Data Index: 1545759 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.1536. Min Act: -0.1700
Data Index: 368608 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.1536. Min Act: -0.1700
Data Index: 632021 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.1224. Min Act: -0.1700
Data Index: 6646830 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.1224. Min Act: -0.1700
Data Index: 3007120 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0911. Min Act: -0.1700
Data Index: 7513332 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0911. Min Act: -0.1700
Data Index: 5506857 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0599. Min Act: -0.1700
Data Index: 961195 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0599. Min Act: -0.1700
Data Index: 6337231 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3411. Min Range: -6.3411
Max Act: 6.0286. Min Act: -0.1700
Data Index: 3681452 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3411. Min Range: -6.3411
Max Act: 5.9974. Min Act: -0.1700
Data Index: 69746 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3411. Min Range: -6.3411
Max Act: 5.9661. Min Act: -0.1700
Data Index: 6643792 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3411. Min Range: -6.3411
Max Act: 5.9661. Min Act: -0.1700
Data Index: 1306397 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3411. Min Range: -6.3411
Max Act: 5.9974. Min Act: -0.1700
Data Index: 3062438 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3411. Min Range: -6.3411
Max Act: 5.9349. Min Act: -0.1700
Data Index: 4066606 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3411. Min Range: -6.3411
Max Act: 5.9036. Min Act: -0.1700
Data Index: 263518 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3411. Min Range: -6.3411
Max Act: 5.9349. Min Act: -0.1700
Data Index: 2105933 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19