Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.8135. Min Act: -0.1700
Data Index: 4749450 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.7198. Min Act: -0.1700
Data Index: 5483296 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.4385. Min Act: -0.1700
Data Index: 8334121 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.2823. Min Act: -0.1700
Data Index: 61805 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.2823. Min Act: -0.1700
Data Index: 2170440 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.2823. Min Act: -0.1700
Data Index: 930390 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.2198. Min Act: -0.1700
Data Index: 1570862 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.2198. Min Act: -0.1700
Data Index: 2192897 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.1885. Min Act: -0.1700
Data Index: 4183191 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.1573. Min Act: -0.1700
Data Index: 1491265 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.1573. Min Act: -0.1700
Data Index: 1871726 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.1573. Min Act: -0.1700
Data Index: 7426006 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.1260. Min Act: -0.1700
Data Index: 6737439 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.0948. Min Act: -0.1700
Data Index: 2948302 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.0948. Min Act: -0.1700
Data Index: 3129884 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.0635. Min Act: -0.1700
Data Index: 8188472 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.0323. Min Act: -0.1700
Data Index: 2002365 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.0010. Min Act: -0.1700
Data Index: 502559 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.0010. Min Act: -0.1700
Data Index: 5493108 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.0010. Min Act: -0.1700
Data Index: 5395720 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19