Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 312 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.5557. Min Act: -0.1700
Data Index: 7066992 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.5244. Min Act: -0.1700
Data Index: 7533018 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.4932. Min Act: -0.1700
Data Index: 2034881 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.4619. Min Act: -0.1700
Data Index: 8117009 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.4307. Min Act: -0.1700
Data Index: 6771215 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.4307. Min Act: -0.1700
Data Index: 1068033 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.4307. Min Act: -0.1700
Data Index: 5291015 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.4307. Min Act: -0.1700
Data Index: 2789943 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.4307. Min Act: -0.1700
Data Index: 8549031 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.3682. Min Act: -0.1700
Data Index: 7557521 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.3682. Min Act: -0.1700
Data Index: 3885101 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.3682. Min Act: -0.1700
Data Index: 6905803 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.3682. Min Act: -0.1700
Data Index: 4085235 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.3369. Min Act: -0.1700
Data Index: 1594609 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.3369. Min Act: -0.1700
Data Index: 3890929 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.3369. Min Act: -0.1700
Data Index: 5703160 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.3369. Min Act: -0.1700
Data Index: 7673819 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.2744. Min Act: -0.1700
Data Index: 7312370 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.2744. Min Act: -0.1700
Data Index: 3747767 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5557. Min Range: -4.5557
Max Act: 4.2744. Min Act: -0.1700
Data Index: 3897011 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19