Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2189 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3473. Min Range: -5.3473
Max Act: 5.3473. Min Act: -0.1700
Data Index: 1186699 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.9411. Min Act: -0.1700
Data Index: 5467817 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.8473. Min Act: -0.1700
Data Index: 5848216 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.8161. Min Act: -0.1700
Data Index: 1526880 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.7536. Min Act: -0.1700
Data Index: 7146519 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.7536. Min Act: -0.1700
Data Index: 897788 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.7536. Min Act: -0.1700
Data Index: 4255136 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.6911. Min Act: -0.1700
Data Index: 2321960 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.7223. Min Act: -0.1700
Data Index: 2389696 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.7223. Min Act: -0.1700
Data Index: 3637811 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.7223. Min Act: -0.1700
Data Index: 8357148 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.6911. Min Act: -0.1700
Data Index: 1538236 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.6911. Min Act: -0.1700
Data Index: 6914736 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.6911. Min Act: -0.1700
Data Index: 4808343 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.6911. Min Act: -0.1700
Data Index: 2532122 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.6911. Min Act: -0.1700
Data Index: 2249620 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.6911. Min Act: -0.1700
Data Index: 1237975 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.6598. Min Act: -0.1700
Data Index: 1640072 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.6598. Min Act: -0.1700
Data Index: 1340842 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3473. Min Range: -5.3473
Max Act: 4.6598. Min Act: -0.1700
Data Index: 7426762 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19