Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4420 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3796. Min Range: -8.3796
Max Act: 8.3796. Min Act: -0.1700
Data Index: 1962562 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3796. Min Range: -8.3796
Max Act: 8.2546. Min Act: -0.1700
Data Index: 5163247 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3796. Min Range: -8.3796
Max Act: 8.1921. Min Act: -0.1700
Data Index: 672245 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3796. Min Range: -8.3796
Max Act: 8.1921. Min Act: -0.1700
Data Index: 2712561 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3796. Min Range: -8.3796
Max Act: 8.0358. Min Act: -0.1700
Data Index: 7829911 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.9733. Min Act: -0.1700
Data Index: 5982816 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.9733. Min Act: -0.1700
Data Index: 1040671 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.9733. Min Act: -0.1700
Data Index: 1531739 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3796. Min Range: -8.3796
Max Act: 8.0046. Min Act: -0.1700
Data Index: 2341171 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.9733. Min Act: -0.1700
Data Index: 8238460 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.9108. Min Act: -0.1700
Data Index: 7711083 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.8796. Min Act: -0.1700
Data Index: 7364621 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.8483. Min Act: -0.1700
Data Index: 8378247 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.8483. Min Act: -0.1700
Data Index: 1819413 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.8796. Min Act: -0.1700
Data Index: 6620804 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.8171. Min Act: -0.1700
Data Index: 8039441 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.8171. Min Act: -0.1700
Data Index: 372656 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.8171. Min Act: -0.1700
Data Index: 6101881 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.7546. Min Act: -0.1700
Data Index: 1733427 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3796. Min Range: -8.3796
Max Act: 7.7233. Min Act: -0.1700
Data Index: 4757900 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19