Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1357 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.6672. Min Act: -0.1700
Data Index: 516919 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.4172. Min Act: -0.1700
Data Index: 342976 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.2922. Min Act: -0.1700
Data Index: 4680791 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.2922. Min Act: -0.1700
Data Index: 4675791 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.2922. Min Act: -0.1700
Data Index: 1419554 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.3547. Min Act: -0.1700
Data Index: 7300968 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.2297. Min Act: -0.1700
Data Index: 2041823 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.1672. Min Act: -0.1700
Data Index: 1337969 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.1672. Min Act: -0.1700
Data Index: 5044568 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.0422. Min Act: -0.1700
Data Index: 4596816 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.0422. Min Act: -0.1700
Data Index: 2880320 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.1047. Min Act: -0.1700
Data Index: 1354356 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.0422. Min Act: -0.1700
Data Index: 4495522 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6672. Min Range: -12.6672
Max Act: 12.0422. Min Act: -0.1700
Data Index: 7599540 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6672. Min Range: -12.6672
Max Act: 11.9797. Min Act: -0.1700
Data Index: 6564805 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6672. Min Range: -12.6672
Max Act: 11.9797. Min Act: -0.1700
Data Index: 5775168 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6672. Min Range: -12.6672
Max Act: 11.8547. Min Act: -0.1700
Data Index: 4414640 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6672. Min Range: -12.6672
Max Act: 11.8547. Min Act: -0.1700
Data Index: 1275713 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6672. Min Range: -12.6672
Max Act: 11.8547. Min Act: -0.1700
Data Index: 3889764 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6672. Min Range: -12.6672
Max Act: 11.8547. Min Act: -0.1700
Data Index: 6150286 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19