Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3230 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.8463. Min Act: -0.1700
Data Index: 726803 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.7838. Min Act: -0.1700
Data Index: 1282828 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.4713. Min Act: -0.1700
Data Index: 3732523 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.4401. Min Act: -0.1700
Data Index: 6693945 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.4088. Min Act: -0.1700
Data Index: 3052462 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.3776. Min Act: -0.1700
Data Index: 3873049 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.3151. Min Act: -0.1700
Data Index: 3943966 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.3463. Min Act: -0.1700
Data Index: 3777508 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.3151. Min Act: -0.1700
Data Index: 5447648 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.3151. Min Act: -0.1700
Data Index: 2054071 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.2526. Min Act: -0.1700
Data Index: 6193879 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.2838. Min Act: -0.1700
Data Index: 3492059 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.2838. Min Act: -0.1700
Data Index: 698008 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.2838. Min Act: -0.1700
Data Index: 6978188 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.2838. Min Act: -0.1700
Data Index: 2889269 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.2838. Min Act: -0.1700
Data Index: 5960470 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.2213. Min Act: -0.1700
Data Index: 6260061 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.2213. Min Act: -0.1700
Data Index: 4864331 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.2213. Min Act: -0.1700
Data Index: 2521902 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8463. Min Range: -7.8463
Max Act: 7.2213. Min Act: -0.1700
Data Index: 3027194 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19