Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2565. Min Range: -7.2565
Max Act: 7.2565. Min Act: -0.1700
Data Index: 2404350 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2565. Min Range: -7.2565
Max Act: 7.0377. Min Act: -0.1700
Data Index: 2561912 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.9752. Min Act: -0.1700
Data Index: 8227780 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.9752. Min Act: -0.1700
Data Index: 5414102 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.9440. Min Act: -0.1700
Data Index: 3137936 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.8815. Min Act: -0.1700
Data Index: 5236875 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.8815. Min Act: -0.1700
Data Index: 8311873 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.8815. Min Act: -0.1700
Data Index: 8311876 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.8190. Min Act: -0.1700
Data Index: 2219561 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.8190. Min Act: -0.1700
Data Index: 2636988 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.8190. Min Act: -0.1700
Data Index: 2733754 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.7877. Min Act: -0.1700
Data Index: 1954712 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.7877. Min Act: -0.1700
Data Index: 3550705 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.7565. Min Act: -0.1700
Data Index: 1273811 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.7565. Min Act: -0.1700
Data Index: 5905238 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.7565. Min Act: -0.1700
Data Index: 2771745 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.7252. Min Act: -0.1700
Data Index: 1605275 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.7252. Min Act: -0.1700
Data Index: 609224 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.7252. Min Act: -0.1700
Data Index: 5892176 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2565. Min Range: -7.2565
Max Act: 6.6940. Min Act: -0.1700
Data Index: 7222700 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19