Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1380 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.5495. Min Act: -0.1700
Data Index: 5281886 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.2995. Min Act: -0.1700
Data Index: 5522284 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.2370. Min Act: -0.1700
Data Index: 2726256 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.2370. Min Act: -0.1700
Data Index: 4709960 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.2370. Min Act: -0.1700
Data Index: 8032232 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.2058. Min Act: -0.1700
Data Index: 4035819 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.2058. Min Act: -0.1700
Data Index: 2924945 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.2058. Min Act: -0.1700
Data Index: 4070901 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.2058. Min Act: -0.1700
Data Index: 5352509 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.1745. Min Act: -0.1700
Data Index: 5224642 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.1433. Min Act: -0.1700
Data Index: 2163485 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.1433. Min Act: -0.1700
Data Index: 1057353 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.1433. Min Act: -0.1700
Data Index: 1790520 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.1433. Min Act: -0.1700
Data Index: 8399430 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.1120. Min Act: -0.1700
Data Index: 7129343 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.0808. Min Act: -0.1700
Data Index: 1033827 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.0808. Min Act: -0.1700
Data Index: 2871972 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.0808. Min Act: -0.1700
Data Index: 7808986 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.0495. Min Act: -0.1700
Data Index: 7260625 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5495. Min Range: -5.5495
Max Act: 5.0495. Min Act: -0.1700
Data Index: 4741505 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19