Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1422 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.7624. Min Act: -0.1700
Data Index: 7417742 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.7304. Min Act: -0.1700
Data Index: 2834039 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.7304. Min Act: -0.1700
Data Index: 1798769 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.6504. Min Act: -0.1700
Data Index: 7589113 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.6183. Min Act: -0.1700
Data Index: 4984569 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.6343. Min Act: -0.1700
Data Index: 5375819 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.6022. Min Act: -0.1700
Data Index: 2769459 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.6183. Min Act: -0.1700
Data Index: 8375814 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.6183. Min Act: -0.1700
Data Index: 3505245 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.5700. Min Act: -0.1700
Data Index: 7417743 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.5700. Min Act: -0.1700
Data Index: 3841451 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.5700. Min Act: -0.1700
Data Index: 8401541 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.5700. Min Act: -0.1700
Data Index: 7220968 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.5861. Min Act: -0.1700
Data Index: 1597298 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.5700. Min Act: -0.1700
Data Index: 4822884 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.5538. Min Act: -0.1700
Data Index: 3422154 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.5538. Min Act: -0.1700
Data Index: 2062899 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.5700. Min Act: -0.1700
Data Index: 5051810 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.5377. Min Act: -0.1700
Data Index: 500772 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7624. Min Range: -2.7624
Max Act: 2.5538. Min Act: -0.1700
Data Index: 5300048 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19