Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 834 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.7169. Min Act: -0.1700
Data Index: 4429843 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.6231. Min Act: -0.1700
Data Index: 5896104 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.6231. Min Act: -0.1700
Data Index: 700952 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4981. Min Act: -0.1700
Data Index: 5610803 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4981. Min Act: -0.1700
Data Index: 4984797 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4981. Min Act: -0.1700
Data Index: 6851106 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4981. Min Act: -0.1700
Data Index: 6585243 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4669. Min Act: -0.1700
Data Index: 2062388 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4669. Min Act: -0.1700
Data Index: 4256491 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4669. Min Act: -0.1700
Data Index: 702157 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4669. Min Act: -0.1700
Data Index: 6396085 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4356. Min Act: -0.1700
Data Index: 8830115 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4356. Min Act: -0.1700
Data Index: 238920 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4356. Min Act: -0.1700
Data Index: 3276673 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4356. Min Act: -0.1700
Data Index: 7497457 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4044. Min Act: -0.1700
Data Index: 6830529 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4044. Min Act: -0.1700
Data Index: 277319 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.3731. Min Act: -0.1700
Data Index: 7507305 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.3419. Min Act: -0.1700
Data Index: 3824267 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.3419. Min Act: -0.1700
Data Index: 5631440 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19