Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3180 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0605. Min Range: -8.0605
Max Act: 8.0605. Min Act: -0.1700
Data Index: 6622097 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.8730. Min Act: -0.1700
Data Index: 4594953 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.8730. Min Act: -0.1700
Data Index: 6932225 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.8105. Min Act: -0.1700
Data Index: 7743943 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.7793. Min Act: -0.1700
Data Index: 378049 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.7480. Min Act: -0.1700
Data Index: 8730850 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.7168. Min Act: -0.1700
Data Index: 8807353 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.7480. Min Act: -0.1700
Data Index: 2211432 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.7168. Min Act: -0.1700
Data Index: 7631985 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.7168. Min Act: -0.1700
Data Index: 1582102 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.7168. Min Act: -0.1700
Data Index: 3321741 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.7168. Min Act: -0.1700
Data Index: 66649 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.6855. Min Act: -0.1700
Data Index: 548677 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.7168. Min Act: -0.1700
Data Index: 6878328 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.6855. Min Act: -0.1700
Data Index: 3994873 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.6543. Min Act: -0.1700
Data Index: 5555016 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.6543. Min Act: -0.1700
Data Index: 7606121 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.6543. Min Act: -0.1700
Data Index: 7431670 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.6230. Min Act: -0.1700
Data Index: 6687969 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0605. Min Range: -8.0605
Max Act: 7.5918. Min Act: -0.1700
Data Index: 6200128 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19