Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4171 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.3520. Min Act: -0.1700
Data Index: 6420698 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.1645. Min Act: -0.1700
Data Index: 5982942 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.1645. Min Act: -0.1700
Data Index: 1783005 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.1645. Min Act: -0.1700
Data Index: 3628998 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.1645. Min Act: -0.1700
Data Index: 3026364 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.1645. Min Act: -0.1700
Data Index: 6763949 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.1645. Min Act: -0.1700
Data Index: 2222456 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.1020. Min Act: -0.1700
Data Index: 925397 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.0707. Min Act: -0.1700
Data Index: 4557935 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.1020. Min Act: -0.1700
Data Index: 4007552 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.1020. Min Act: -0.1700
Data Index: 4917770 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.0082. Min Act: -0.1700
Data Index: 3027894 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.0082. Min Act: -0.1700
Data Index: 5994206 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.0082. Min Act: -0.1700
Data Index: 4557937 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3520. Min Range: -5.3520
Max Act: 5.0082. Min Act: -0.1700
Data Index: 8827604 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3520. Min Range: -5.3520
Max Act: 4.9770. Min Act: -0.1700
Data Index: 7897760 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3520. Min Range: -5.3520
Max Act: 4.9770. Min Act: -0.1700
Data Index: 4600920 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3520. Min Range: -5.3520
Max Act: 4.9457. Min Act: -0.1700
Data Index: 6153743 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3520. Min Range: -5.3520
Max Act: 4.9457. Min Act: -0.1700
Data Index: 460293 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3520. Min Range: -5.3520
Max Act: 4.9145. Min Act: -0.1700
Data Index: 4039922 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19