Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1816 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.6560. Min Act: -0.1700
Data Index: 1885620 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.6560. Min Act: -0.1700
Data Index: 6799757 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.6247. Min Act: -0.1700
Data Index: 1666547 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.5310. Min Act: -0.1700
Data Index: 5033090 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4997. Min Act: -0.1700
Data Index: 3178110 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4997. Min Act: -0.1700
Data Index: 4960338 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4372. Min Act: -0.1700
Data Index: 3867936 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4372. Min Act: -0.1700
Data Index: 1314689 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4685. Min Act: -0.1700
Data Index: 5030285 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4372. Min Act: -0.1700
Data Index: 7231725 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4372. Min Act: -0.1700
Data Index: 3597062 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4060. Min Act: -0.1700
Data Index: 8353900 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4372. Min Act: -0.1700
Data Index: 6350545 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4685. Min Act: -0.1700
Data Index: 8416143 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4372. Min Act: -0.1700
Data Index: 7552194 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4372. Min Act: -0.1700
Data Index: 5469636 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4372. Min Act: -0.1700
Data Index: 8115283 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4060. Min Act: -0.1700
Data Index: 5469634 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4372. Min Act: -0.1700
Data Index: 4018578 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6560. Min Range: -5.6560
Max Act: 5.4060. Min Act: -0.1700
Data Index: 4024302 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19