Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5838. Min Range: -12.5838
Max Act: 12.5838. Min Act: -0.1700
Data Index: 7144028 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5838. Min Range: -12.5838
Max Act: 12.2713. Min Act: -0.1700
Data Index: 25369 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5838. Min Range: -12.5838
Max Act: 12.2713. Min Act: -0.1700
Data Index: 6414900 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5838. Min Range: -12.5838
Max Act: 12.1463. Min Act: -0.1700
Data Index: 2655360 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5838. Min Range: -12.5838
Max Act: 12.0838. Min Act: -0.1700
Data Index: 4421659 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5838. Min Range: -12.5838
Max Act: 12.0213. Min Act: -0.1700
Data Index: 8669860 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.8338. Min Act: -0.1700
Data Index: 4989331 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.8338. Min Act: -0.1696
Data Index: 2655359 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.8338. Min Act: -0.1700
Data Index: 7014207 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.8338. Min Act: -0.1700
Data Index: 426252 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.6463. Min Act: -0.1690
Data Index: 8069669 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.7088. Min Act: -0.1700
Data Index: 2850414 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.6463. Min Act: -0.1695
Data Index: 2456008 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.5838. Min Act: -0.1699
Data Index: 2950767 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.5213. Min Act: -0.1700
Data Index: 219666 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.5213. Min Act: -0.1700
Data Index: 5579311 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.4588. Min Act: -0.1699
Data Index: 7393593 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.4588. Min Act: -0.1700
Data Index: 8669857 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.3963. Min Act: -0.1700
Data Index: 2609283 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5838. Min Range: -12.5838
Max Act: 11.3338. Min Act: -0.1699
Data Index: 2883903 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19