Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4198 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7171. Min Range: -9.7171
Max Act: 9.7171. Min Act: -0.1700
Data Index: 4313484 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7171. Min Range: -9.7171
Max Act: 9.4046. Min Act: -0.1700
Data Index: 1683127 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7171. Min Range: -9.7171
Max Act: 9.2796. Min Act: -0.1700
Data Index: 3798073 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7171. Min Range: -9.7171
Max Act: 9.2171. Min Act: -0.1700
Data Index: 2156803 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7171. Min Range: -9.7171
Max Act: 9.2171. Min Act: -0.1700
Data Index: 2880156 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7171. Min Range: -9.7171
Max Act: 9.0921. Min Act: -0.1700
Data Index: 4616942 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7171. Min Range: -9.7171
Max Act: 9.0296. Min Act: -0.1700
Data Index: 1852317 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.9671. Min Act: -0.1700
Data Index: 2292011 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.9671. Min Act: -0.1700
Data Index: 8614796 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.8421. Min Act: -0.1700
Data Index: 5138065 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.7796. Min Act: -0.1700
Data Index: 5674836 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.7796. Min Act: -0.1700
Data Index: 5660722 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.7796. Min Act: -0.1700
Data Index: 1454590 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.7796. Min Act: -0.1700
Data Index: 5418990 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.7171. Min Act: -0.1700
Data Index: 1848430 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.6546. Min Act: -0.1700
Data Index: 7661571 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.5921. Min Act: -0.1700
Data Index: 7858148 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.5921. Min Act: -0.1700
Data Index: 8671459 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.5296. Min Act: -0.1700
Data Index: 4879006 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7171. Min Range: -9.7171
Max Act: 8.4671. Min Act: -0.1700
Data Index: 2777096 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19