Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6084 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.5334. Min Act: -0.1700
Data Index: 4965471 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.5172. Min Act: -0.1700
Data Index: 4965475 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.5010. Min Act: -0.1700
Data Index: 6935787 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.4848. Min Act: -0.1700
Data Index: 4965470 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.4686. Min Act: -0.1700
Data Index: 8285238 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.4686. Min Act: -0.1700
Data Index: 4567944 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.4524. Min Act: -0.1700
Data Index: 1646307 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.4524. Min Act: -0.1700
Data Index: 6935799 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.4361. Min Act: -0.1700
Data Index: 7157510 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.4198. Min Act: -0.1700
Data Index: 7675934 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.4198. Min Act: -0.1700
Data Index: 6206150 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.3872. Min Act: -0.1700
Data Index: 8804638 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.4035. Min Act: -0.1700
Data Index: 1149174 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.3872. Min Act: -0.1700
Data Index: 386323 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.3708. Min Act: -0.1700
Data Index: 1749374 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.4035. Min Act: -0.1700
Data Index: 3863909 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.3708. Min Act: -0.1700
Data Index: 6100972 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.3708. Min Act: -0.1700
Data Index: 189762 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.3545. Min Act: -0.1700
Data Index: 4084904 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5334. Min Range: -2.5334
Max Act: 2.3545. Min Act: -0.1700
Data Index: 5236226 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19