Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2514 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.9838. Min Act: -0.1700
Data Index: 4867001 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.9838. Min Act: -0.1700
Data Index: 4948941 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.8588. Min Act: -0.1700
Data Index: 6442867 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.7963. Min Act: -0.1700
Data Index: 7841479 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.8588. Min Act: -0.1700
Data Index: 7920804 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.7963. Min Act: -0.1700
Data Index: 3748065 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.7963. Min Act: -0.1700
Data Index: 7928253 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.7963. Min Act: -0.1700
Data Index: 154684 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.7963. Min Act: -0.1700
Data Index: 7683573 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.7338. Min Act: -0.1700
Data Index: 2932476 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.7338. Min Act: -0.1700
Data Index: 3170356 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.6713. Min Act: -0.1700
Data Index: 1942248 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.7338. Min Act: -0.1700
Data Index: 6798428 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.7338. Min Act: -0.1700
Data Index: 2041775 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.6713. Min Act: -0.1700
Data Index: 3812580 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.6713. Min Act: -0.1700
Data Index: 403002 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.6713. Min Act: -0.1700
Data Index: 4587610 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.6713. Min Act: -0.1700
Data Index: 8091130 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.6088. Min Act: -0.1700
Data Index: 83539 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9838. Min Range: -7.9838
Max Act: 7.6088. Min Act: -0.1700
Data Index: 7095953 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19