Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1555. Min Range: -6.1555
Max Act: 6.1555. Min Act: -0.1700
Data Index: 5461718 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1555. Min Range: -6.1555
Max Act: 6.0930. Min Act: -0.1700
Data Index: 4819012 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1555. Min Range: -6.1555
Max Act: 6.0305. Min Act: -0.1700
Data Index: 1635636 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.9680. Min Act: -0.1700
Data Index: 1212380 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.9368. Min Act: -0.1700
Data Index: 4885629 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.9368. Min Act: -0.1700
Data Index: 6759740 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.9368. Min Act: -0.1700
Data Index: 3078802 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.9680. Min Act: -0.1700
Data Index: 4257953 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.8743. Min Act: -0.1700
Data Index: 8210983 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.9055. Min Act: -0.1700
Data Index: 6063413 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.8743. Min Act: -0.1700
Data Index: 1716729 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.8743. Min Act: -0.1700
Data Index: 3220099 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.8743. Min Act: -0.1700
Data Index: 7454863 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.8118. Min Act: -0.1700
Data Index: 4811495 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.8430. Min Act: -0.1700
Data Index: 6668594 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.8118. Min Act: -0.1700
Data Index: 1904923 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.7805. Min Act: -0.1700
Data Index: 7794006 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.8118. Min Act: -0.1700
Data Index: 6658540 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.8118. Min Act: -0.1700
Data Index: 7181905 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.7805. Min Act: -0.1700
Data Index: 4109263 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19