Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2465 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.3661. Min Act: -0.1700
Data Index: 7889281 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.3349. Min Act: -0.1700
Data Index: 2053052 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.3349. Min Act: -0.1700
Data Index: 3668581 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.3036. Min Act: -0.1700
Data Index: 5398083 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.2724. Min Act: -0.1700
Data Index: 44625 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.2411. Min Act: -0.1700
Data Index: 143766 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.2411. Min Act: -0.1700
Data Index: 4351765 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.2411. Min Act: -0.1700
Data Index: 2499703 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.2099. Min Act: -0.1700
Data Index: 7607020 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.2099. Min Act: -0.1700
Data Index: 4353180 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.1786. Min Act: -0.1700
Data Index: 679007 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.2099. Min Act: -0.1700
Data Index: 2918208 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.1786. Min Act: -0.1700
Data Index: 5454239 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.1786. Min Act: -0.1700
Data Index: 6900953 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.1786. Min Act: -0.1700
Data Index: 2587576 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.1786. Min Act: -0.1700
Data Index: 2509067 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.1786. Min Act: -0.1700
Data Index: 1822833 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.1786. Min Act: -0.1700
Data Index: 1892385 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.2099. Min Act: -0.1700
Data Index: 990205 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3661. Min Range: -4.3661
Max Act: 4.1786. Min Act: -0.1700
Data Index: 5282188 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19