Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3172 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5310. Min Range: -6.5310
Max Act: 6.5310. Min Act: -0.1700
Data Index: 8410816 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5310. Min Range: -6.5310
Max Act: 6.4060. Min Act: -0.1700
Data Index: 3489309 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5310. Min Range: -6.5310
Max Act: 6.1560. Min Act: -0.1700
Data Index: 8036077 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5310. Min Range: -6.5310
Max Act: 6.1560. Min Act: -0.1700
Data Index: 3495899 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5310. Min Range: -6.5310
Max Act: 6.0623. Min Act: -0.1700
Data Index: 2010984 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5310. Min Range: -6.5310
Max Act: 6.0623. Min Act: -0.1700
Data Index: 4466713 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.9685. Min Act: -0.1700
Data Index: 8672944 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.9373. Min Act: -0.1700
Data Index: 5181413 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.9060. Min Act: -0.1700
Data Index: 4046040 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.8435. Min Act: -0.1700
Data Index: 2419403 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.8748. Min Act: -0.1700
Data Index: 1373015 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.8435. Min Act: -0.1700
Data Index: 393021 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.7810. Min Act: -0.1700
Data Index: 3044316 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.7810. Min Act: -0.1700
Data Index: 3885169 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.7810. Min Act: -0.1700
Data Index: 4551780 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.7498. Min Act: -0.1700
Data Index: 1569842 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.6873. Min Act: -0.1700
Data Index: 4875329 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.6873. Min Act: -0.1700
Data Index: 7692856 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.6873. Min Act: -0.1700
Data Index: 1719360 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5310. Min Range: -6.5310
Max Act: 5.6560. Min Act: -0.1700
Data Index: 5655032 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19