Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5085 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.4594. Min Act: -0.1700
Data Index: 2403933 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.2094. Min Act: -0.1700
Data Index: 6674686 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.1469. Min Act: -0.1700
Data Index: 3767059 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.0531. Min Act: -0.1700
Data Index: 5231371 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.0219. Min Act: -0.1700
Data Index: 6274789 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9906. Min Act: -0.1700
Data Index: 1162719 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9906. Min Act: -0.1700
Data Index: 5849414 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9906. Min Act: -0.1700
Data Index: 239313 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9594. Min Act: -0.1700
Data Index: 3678883 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9594. Min Act: -0.1700
Data Index: 2627637 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.8969. Min Act: -0.1700
Data Index: 2181526 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.8969. Min Act: -0.1700
Data Index: 2430346 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.8656. Min Act: -0.1700
Data Index: 4240105 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.8656. Min Act: -0.1700
Data Index: 5567038 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.8344. Min Act: -0.1700
Data Index: 7217026 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.8656. Min Act: -0.1700
Data Index: 7852033 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.8344. Min Act: -0.1700
Data Index: 1193442 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.8031. Min Act: -0.1700
Data Index: 1423829 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.8031. Min Act: -0.1700
Data Index: 1833914 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.8031. Min Act: -0.1700
Data Index: 6134981 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19