Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3922 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.7649. Min Act: -0.1700
Data Index: 8179948 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.7649. Min Act: -0.1700
Data Index: 2329285 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.7179. Min Act: -0.1700
Data Index: 8701568 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.7023. Min Act: -0.1700
Data Index: 1893234 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.6710. Min Act: -0.1700
Data Index: 3700106 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.6397. Min Act: -0.1700
Data Index: 5459194 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.6084. Min Act: -0.1700
Data Index: 1371659 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.6241. Min Act: -0.1700
Data Index: 165180 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.5928. Min Act: -0.1700
Data Index: 862609 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.6084. Min Act: -0.1700
Data Index: 4477833 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.6084. Min Act: -0.1700
Data Index: 7761817 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.6084. Min Act: -0.1700
Data Index: 3236454 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.6084. Min Act: -0.1700
Data Index: 5289566 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.5928. Min Act: -0.1700
Data Index: 3243983 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.5458. Min Act: -0.1700
Data Index: 1433854 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.5458. Min Act: -0.1700
Data Index: 7599006 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.5458. Min Act: -0.1700
Data Index: 6359836 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.5145. Min Act: -0.1700
Data Index: 7572761 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.5145. Min Act: -0.1700
Data Index: 3529279 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7649. Min Range: -3.7649
Max Act: 3.5145. Min Act: -0.1700
Data Index: 4698434 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19