Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5317 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3035. Min Range: -4.3035
Max Act: 4.3035. Min Act: -0.1700
Data Index: 8333016 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3035. Min Range: -4.3035
Max Act: 4.1473. Min Act: -0.1700
Data Index: 5766655 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3035. Min Range: -4.3035
Max Act: 4.0535. Min Act: -0.1700
Data Index: 494613 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3035. Min Range: -4.3035
Max Act: 4.0535. Min Act: -0.1700
Data Index: 1316074 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3035. Min Range: -4.3035
Max Act: 4.0535. Min Act: -0.1700
Data Index: 1860587 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.9597. Min Act: -0.1700
Data Index: 8025260 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.8972. Min Act: -0.1700
Data Index: 5281642 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.8972. Min Act: -0.1700
Data Index: 6628777 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.8659. Min Act: -0.1700
Data Index: 1494013 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.8346. Min Act: -0.1700
Data Index: 4509579 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.8034. Min Act: -0.1700
Data Index: 1860311 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.8034. Min Act: -0.1700
Data Index: 6775563 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.7564. Min Act: -0.1700
Data Index: 3524318 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.7564. Min Act: -0.1700
Data Index: 6489411 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.7564. Min Act: -0.1700
Data Index: 5421120 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.7564. Min Act: -0.1700
Data Index: 7371086 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.7252. Min Act: -0.1700
Data Index: 5787937 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.7408. Min Act: -0.1700
Data Index: 6489412 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.7252. Min Act: -0.1700
Data Index: 3710929 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3035. Min Range: -4.3035
Max Act: 3.7252. Min Act: -0.1700
Data Index: 8381133 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19