Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 574 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.5356. Min Act: -0.1700
Data Index: 6701015 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.4731. Min Act: -0.1700
Data Index: 5779527 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.4418. Min Act: -0.1700
Data Index: 5176575 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.3793. Min Act: -0.1700
Data Index: 2951309 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.3793. Min Act: -0.1700
Data Index: 7500708 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.3793. Min Act: -0.1700
Data Index: 1435697 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.3481. Min Act: -0.1700
Data Index: 690716 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.3481. Min Act: -0.1700
Data Index: 7901163 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.3168. Min Act: -0.1700
Data Index: 5176576 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.2856. Min Act: -0.1700
Data Index: 2151702 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.3168. Min Act: -0.1700
Data Index: 5144684 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.2856. Min Act: -0.1700
Data Index: 5888855 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.2543. Min Act: -0.1700
Data Index: 6077772 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.2543. Min Act: -0.1700
Data Index: 3395458 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.2543. Min Act: -0.1700
Data Index: 301039 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.2856. Min Act: -0.1700
Data Index: 7130840 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.2231. Min Act: -0.1700
Data Index: 6046865 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.2231. Min Act: -0.1700
Data Index: 155488 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.2231. Min Act: -0.1700
Data Index: 6789561 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5356. Min Range: -5.5356
Max Act: 5.2231. Min Act: -0.1700
Data Index: 6655643 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19