Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.9621. Min Act: -0.1700
Data Index: 8497634 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.9779. Min Act: -0.1700
Data Index: 7447320 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.8988. Min Act: -0.1700
Data Index: 7231034 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.8988. Min Act: -0.1700
Data Index: 6717185 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.8670. Min Act: -0.1700
Data Index: 8033670 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.9146. Min Act: -0.1700
Data Index: 8289406 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.8511. Min Act: -0.1700
Data Index: 913634 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.8829. Min Act: -0.1700
Data Index: 7528380 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.8670. Min Act: -0.1700
Data Index: 8430314 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.8034. Min Act: -0.1700
Data Index: 4437949 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.8193. Min Act: -0.1700
Data Index: 1156016 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.8034. Min Act: -0.1700
Data Index: 1398347 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.7556. Min Act: -0.1700
Data Index: 5266004 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.7875. Min Act: -0.1700
Data Index: 2415229 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.7875. Min Act: -0.1700
Data Index: 5965486 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.7875. Min Act: -0.1700
Data Index: 2850504 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.7716. Min Act: -0.1700
Data Index: 7864598 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.7716. Min Act: -0.1700
Data Index: 5107084 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.7396. Min Act: -0.1700
Data Index: 8255216 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9779. Min Range: -2.9779
Max Act: 2.7237. Min Act: -0.1700
Data Index: 5462124 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19