Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0265. Min Range: -6.0265
Max Act: 6.0265. Min Act: -0.1700
Data Index: 5401742 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.9952. Min Act: -0.1700
Data Index: 4839053 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.8702. Min Act: -0.1700
Data Index: 3940690 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.9015. Min Act: -0.1700
Data Index: 2576530 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.8702. Min Act: -0.1700
Data Index: 7255923 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.8390. Min Act: -0.1700
Data Index: 6200754 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.7765. Min Act: -0.1700
Data Index: 6654313 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.7765. Min Act: -0.1700
Data Index: 6622076 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.7140. Min Act: -0.1700
Data Index: 2040070 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.7140. Min Act: -0.1700
Data Index: 4000390 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.7140. Min Act: -0.1700
Data Index: 4169979 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.7452. Min Act: -0.1700
Data Index: 2858405 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.6515. Min Act: -0.1700
Data Index: 1028309 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.7140. Min Act: -0.1700
Data Index: 2900566 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.6515. Min Act: -0.1700
Data Index: 1517133 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.6515. Min Act: -0.1700
Data Index: 7726720 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.6202. Min Act: -0.1700
Data Index: 6652491 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.6202. Min Act: -0.1700
Data Index: 2255395 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.5890. Min Act: -0.1700
Data Index: 2438268 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0265. Min Range: -6.0265
Max Act: 5.6202. Min Act: -0.1700
Data Index: 4097486 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19