Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4296. Min Range: -9.4296
Max Act: 9.4296. Min Act: -0.1700
Data Index: 3063451 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4296. Min Range: -9.4296
Max Act: 9.4296. Min Act: -0.1700
Data Index: 1120629 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4296. Min Range: -9.4296
Max Act: 9.3671. Min Act: -0.1700
Data Index: 1122706 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4296. Min Range: -9.4296
Max Act: 9.3046. Min Act: -0.1700
Data Index: 8683377 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4296. Min Range: -9.4296
Max Act: 9.1796. Min Act: -0.1700
Data Index: 7809041 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4296. Min Range: -9.4296
Max Act: 9.1171. Min Act: -0.1700
Data Index: 6103947 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4296. Min Range: -9.4296
Max Act: 9.1171. Min Act: -0.1700
Data Index: 8090984 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4296. Min Range: -9.4296
Max Act: 9.0546. Min Act: -0.1700
Data Index: 462380 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.9296. Min Act: -0.1700
Data Index: 3192830 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.9296. Min Act: -0.1700
Data Index: 6231742 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.8671. Min Act: -0.1700
Data Index: 8549686 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.8671. Min Act: -0.1700
Data Index: 6712822 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.8671. Min Act: -0.1700
Data Index: 2438310 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.8046. Min Act: -0.1700
Data Index: 2827094 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.8046. Min Act: -0.1700
Data Index: 3440143 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.7421. Min Act: -0.1700
Data Index: 6027255 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.7421. Min Act: -0.1700
Data Index: 1586825 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.7421. Min Act: -0.1700
Data Index: 1015875 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.6796. Min Act: -0.1700
Data Index: 1167847 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4296. Min Range: -9.4296
Max Act: 8.6796. Min Act: -0.1700
Data Index: 233631 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19