Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 698 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.9981. Min Act: -0.1700
Data Index: 738540 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.9190. Min Act: -0.1700
Data Index: 1172126 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.9032. Min Act: -0.1700
Data Index: 3887327 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.9032. Min Act: -0.1700
Data Index: 8283823 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8714. Min Act: -0.1700
Data Index: 8009874 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8556. Min Act: -0.1700
Data Index: 1293387 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8556. Min Act: -0.1700
Data Index: 2444800 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8556. Min Act: -0.1700
Data Index: 5112450 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8397. Min Act: -0.1700
Data Index: 826968 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8397. Min Act: -0.1700
Data Index: 3838416 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8397. Min Act: -0.1700
Data Index: 1153333 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8238. Min Act: -0.1700
Data Index: 4805346 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8397. Min Act: -0.1700
Data Index: 5435974 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8238. Min Act: -0.1700
Data Index: 4199149 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8078. Min Act: -0.1700
Data Index: 306896 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8078. Min Act: -0.1700
Data Index: 1649901 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8078. Min Act: -0.1700
Data Index: 8496961 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.8078. Min Act: -0.1700
Data Index: 951980 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.7919. Min Act: -0.1700
Data Index: 3384366 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9981. Min Range: -2.9981
Max Act: 2.7919. Min Act: -0.1700
Data Index: 5885501 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19