Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.9293. Min Act: -0.1700
Data Index: 4686388 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.7106. Min Act: -0.1700
Data Index: 7510523 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.6168. Min Act: -0.1700
Data Index: 4556210 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.5856. Min Act: -0.1700
Data Index: 4594944 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.5543. Min Act: -0.1700
Data Index: 3777758 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.5543. Min Act: -0.1700
Data Index: 8147307 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.3981. Min Act: -0.1700
Data Index: 6302624 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.3668. Min Act: -0.1700
Data Index: 6628258 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.3043. Min Act: -0.1700
Data Index: 8744280 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.3043. Min Act: -0.1700
Data Index: 1365995 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.2731. Min Act: -0.1700
Data Index: 6640130 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.2418. Min Act: -0.1700
Data Index: 5220456 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.2731. Min Act: -0.1700
Data Index: 735820 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.2418. Min Act: -0.1700
Data Index: 8103240 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.2418. Min Act: -0.1700
Data Index: 4543651 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.2106. Min Act: -0.1700
Data Index: 185981 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.1793. Min Act: -0.1700
Data Index: 1090910 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.1793. Min Act: -0.1700
Data Index: 3764867 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.1793. Min Act: -0.1700
Data Index: 5731034 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9293. Min Range: -6.9293
Max Act: 6.1793. Min Act: -0.1700
Data Index: 6297543 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19