Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2264. Min Range: -5.2264
Max Act: 5.2264. Min Act: -0.1700
Data Index: 14604 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2264. Min Range: -5.2264
Max Act: 5.1014. Min Act: -0.1700
Data Index: 7146149 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2264. Min Range: -5.2264
Max Act: 5.0389. Min Act: -0.1700
Data Index: 5956201 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9764. Min Act: -0.1700
Data Index: 4980337 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.8514. Min Act: -0.1700
Data Index: 6578855 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.8514. Min Act: -0.1700
Data Index: 1752856 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.8514. Min Act: -0.1700
Data Index: 4658065 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.8202. Min Act: -0.1700
Data Index: 667043 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.8514. Min Act: -0.1700
Data Index: 4842338 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.7264. Min Act: -0.1700
Data Index: 5463693 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.7264. Min Act: -0.1700
Data Index: 1602134 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.6639. Min Act: -0.1700
Data Index: 43443 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.6639. Min Act: -0.1700
Data Index: 2729826 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.6014. Min Act: -0.1700
Data Index: 7721341 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.6014. Min Act: -0.1700
Data Index: 7751922 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.6327. Min Act: -0.1700
Data Index: 6787374 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.6327. Min Act: -0.1700
Data Index: 2498490 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.6327. Min Act: -0.1700
Data Index: 7510468 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.6014. Min Act: -0.1700
Data Index: 5376774 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.6014. Min Act: -0.1700
Data Index: 590974 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19