Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5480 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3705. Min Range: -5.3705
Max Act: 5.3705. Min Act: -0.1700
Data Index: 2116232 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3705. Min Range: -5.3705
Max Act: 5.1830. Min Act: -0.1700
Data Index: 1575139 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3705. Min Range: -5.3705
Max Act: 5.0580. Min Act: -0.1700
Data Index: 3881137 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3705. Min Range: -5.3705
Max Act: 5.0893. Min Act: -0.1700
Data Index: 2259176 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3705. Min Range: -5.3705
Max Act: 5.0893. Min Act: -0.1700
Data Index: 7676991 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3705. Min Range: -5.3705
Max Act: 5.0580. Min Act: -0.1700
Data Index: 3914291 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3705. Min Range: -5.3705
Max Act: 5.0580. Min Act: -0.1700
Data Index: 8490062 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.9955. Min Act: -0.1700
Data Index: 8631774 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.9955. Min Act: -0.1700
Data Index: 2887904 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.9643. Min Act: -0.1700
Data Index: 157295 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.9643. Min Act: -0.1700
Data Index: 232833 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.9330. Min Act: -0.1700
Data Index: 6878331 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.9330. Min Act: -0.1700
Data Index: 8719584 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.9330. Min Act: -0.1700
Data Index: 1245392 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.9330. Min Act: -0.1700
Data Index: 4558389 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.9018. Min Act: -0.1700
Data Index: 3505404 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.8393. Min Act: -0.1700
Data Index: 4492993 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.8705. Min Act: -0.1700
Data Index: 6524200 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.8705. Min Act: -0.1700
Data Index: 8133720 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3705. Min Range: -5.3705
Max Act: 4.8393. Min Act: -0.1700
Data Index: 4852630 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19