Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3702 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.6539. Min Act: -0.1700
Data Index: 7566824 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.5914. Min Act: -0.1700
Data Index: 4974474 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.5914. Min Act: -0.1700
Data Index: 342701 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.5601. Min Act: -0.1700
Data Index: 4522902 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.5289. Min Act: -0.1700
Data Index: 280974 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.4351. Min Act: -0.1700
Data Index: 169701 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.4664. Min Act: -0.1700
Data Index: 4852198 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.4351. Min Act: -0.1700
Data Index: 1780805 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.4039. Min Act: -0.1700
Data Index: 6518624 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.4664. Min Act: -0.1700
Data Index: 8475474 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.4039. Min Act: -0.1700
Data Index: 3682600 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.4039. Min Act: -0.1700
Data Index: 5432676 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.4039. Min Act: -0.1700
Data Index: 2436411 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.4039. Min Act: -0.1700
Data Index: 761573 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.4039. Min Act: -0.1700
Data Index: 2265989 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.3726. Min Act: -0.1700
Data Index: 5373420 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.3726. Min Act: -0.1700
Data Index: 2306661 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.4039. Min Act: -0.1700
Data Index: 7194009 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.3414. Min Act: -0.1700
Data Index: 853182 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6539. Min Range: -7.6539
Max Act: 7.3414. Min Act: -0.1700
Data Index: 1701245 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19