Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2175 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4834. Min Range: -8.4834
Max Act: 8.4834. Min Act: -0.1700
Data Index: 2669388 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4834. Min Range: -8.4834
Max Act: 8.2959. Min Act: -0.1700
Data Index: 4883030 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4834. Min Range: -8.4834
Max Act: 8.1709. Min Act: -0.1700
Data Index: 5669265 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4834. Min Range: -8.4834
Max Act: 8.1084. Min Act: -0.1700
Data Index: 4494220 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.9834. Min Act: -0.1700
Data Index: 1396652 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.9834. Min Act: -0.1700
Data Index: 4709949 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.9834. Min Act: -0.1700
Data Index: 7258212 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.9209. Min Act: -0.1700
Data Index: 8079901 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.7959. Min Act: -0.1700
Data Index: 3851717 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.8584. Min Act: -0.1700
Data Index: 5638948 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.7334. Min Act: -0.1700
Data Index: 8703297 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.7334. Min Act: -0.1700
Data Index: 8816044 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.7334. Min Act: -0.1700
Data Index: 553520 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.7334. Min Act: -0.1700
Data Index: 3381931 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.7334. Min Act: -0.1700
Data Index: 5286401 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.6084. Min Act: -0.1700
Data Index: 1193802 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.6084. Min Act: -0.1700
Data Index: 3087539 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.6084. Min Act: -0.1700
Data Index: 7323429 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.5772. Min Act: -0.1700
Data Index: 3377009 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.5772. Min Act: -0.1700
Data Index: 5282385 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19