Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2771 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.7995. Min Act: -0.1700
Data Index: 3313015 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.5808. Min Act: -0.1700
Data Index: 1642238 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.5495. Min Act: -0.1700
Data Index: 1579031 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.4870. Min Act: -0.1700
Data Index: 1417085 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.4870. Min Act: -0.1700
Data Index: 2767444 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.4870. Min Act: -0.1700
Data Index: 1692746 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.4558. Min Act: -0.1700
Data Index: 1930758 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.4245. Min Act: -0.1700
Data Index: 3987579 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.3933. Min Act: -0.1700
Data Index: 5090655 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.3933. Min Act: -0.1700
Data Index: 2187686 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.3933. Min Act: -0.1700
Data Index: 1203130 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.4245. Min Act: -0.1700
Data Index: 4472756 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.3308. Min Act: -0.1700
Data Index: 5092275 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.3308. Min Act: -0.1700
Data Index: 1010899 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.3620. Min Act: -0.1700
Data Index: 8667973 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.3308. Min Act: -0.1700
Data Index: 4881039 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.3308. Min Act: -0.1700
Data Index: 2776513 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.3620. Min Act: -0.1700
Data Index: 338158 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.3308. Min Act: -0.1700
Data Index: 5170018 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7995. Min Range: -5.7995
Max Act: 5.2995. Min Act: -0.1700
Data Index: 2092438 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19