Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0147. Min Range: -8.0147
Max Act: 8.0147. Min Act: -0.1700
Data Index: 1289693 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.8897. Min Act: -0.1700
Data Index: 8170167 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.6397. Min Act: -0.1700
Data Index: 320127 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.5772. Min Act: -0.1700
Data Index: 5006363 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.4209. Min Act: -0.1700
Data Index: 498470 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.3897. Min Act: -0.1700
Data Index: 1120460 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.4209. Min Act: -0.1700
Data Index: 463945 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.3272. Min Act: -0.1700
Data Index: 847121 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.2959. Min Act: -0.1700
Data Index: 5992266 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.2647. Min Act: -0.1700
Data Index: 7527742 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.2959. Min Act: -0.1700
Data Index: 3562268 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.2647. Min Act: -0.1700
Data Index: 7248909 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.2647. Min Act: -0.1700
Data Index: 8274276 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.2022. Min Act: -0.1700
Data Index: 1462033 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.2334. Min Act: -0.1700
Data Index: 5225758 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.2022. Min Act: -0.1700
Data Index: 2072743 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.1709. Min Act: -0.1700
Data Index: 4993683 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.2334. Min Act: -0.1700
Data Index: 4920326 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.1709. Min Act: -0.1700
Data Index: 443774 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0147. Min Range: -8.0147
Max Act: 7.1709. Min Act: -0.1700
Data Index: 3732212 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19