Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4182 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.5101. Min Act: -0.1700
Data Index: 8363716 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.4164. Min Act: -0.1700
Data Index: 4671599 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.3226. Min Act: -0.1700
Data Index: 1964577 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.2914. Min Act: -0.1700
Data Index: 4286237 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.2601. Min Act: -0.1700
Data Index: 7269889 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.2601. Min Act: -0.1700
Data Index: 3521659 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.2289. Min Act: -0.1700
Data Index: 5754488 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.1664. Min Act: -0.1700
Data Index: 7281642 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.1664. Min Act: -0.1700
Data Index: 7632109 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.1976. Min Act: -0.1700
Data Index: 4656308 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.1664. Min Act: -0.1700
Data Index: 4337422 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.1976. Min Act: -0.1700
Data Index: 5594836 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.1664. Min Act: -0.1700
Data Index: 8014848 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.1351. Min Act: -0.1700
Data Index: 3797793 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.1351. Min Act: -0.1700
Data Index: 8141298 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.1351. Min Act: -0.1700
Data Index: 5616117 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.0414. Min Act: -0.1700
Data Index: 6318617 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.0414. Min Act: -0.1700
Data Index: 3160788 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.0414. Min Act: -0.1700
Data Index: 749136 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5101. Min Range: -5.5101
Max Act: 5.0101. Min Act: -0.1700
Data Index: 2013961 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19