Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1295 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6664. Min Range: -7.6664
Max Act: 7.6664. Min Act: -0.1700
Data Index: 1639083 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6664. Min Range: -7.6664
Max Act: 7.5727. Min Act: -0.1700
Data Index: 4526323 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6664. Min Range: -7.6664
Max Act: 7.1352. Min Act: -0.1700
Data Index: 6552606 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6664. Min Range: -7.6664
Max Act: 7.1039. Min Act: -0.1700
Data Index: 4496720 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6664. Min Range: -7.6664
Max Act: 7.0414. Min Act: -0.1700
Data Index: 5018142 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.8539. Min Act: -0.1700
Data Index: 1249614 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.8539. Min Act: -0.1700
Data Index: 6275968 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.8539. Min Act: -0.1700
Data Index: 5639946 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.8539. Min Act: -0.1700
Data Index: 1182499 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.8227. Min Act: -0.1700
Data Index: 3798439 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.8227. Min Act: -0.1700
Data Index: 1236320 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.8227. Min Act: -0.1700
Data Index: 748459 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.7602. Min Act: -0.1700
Data Index: 610201 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.7289. Min Act: -0.1700
Data Index: 7323863 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.6664. Min Act: -0.1700
Data Index: 5309088 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.6664. Min Act: -0.1700
Data Index: 8782205 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.6352. Min Act: -0.1700
Data Index: 5664348 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.6352. Min Act: -0.1700
Data Index: 5167948 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.6352. Min Act: -0.1700
Data Index: 5830257 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6664. Min Range: -7.6664
Max Act: 6.6352. Min Act: -0.1700
Data Index: 2165370 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19