Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3253 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5886. Min Act: -0.1700
Data Index: 7076293 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5417. Min Act: -0.1700
Data Index: 135920 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5417. Min Act: -0.1700
Data Index: 6941399 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5260. Min Act: -0.1700
Data Index: 13253 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5417. Min Act: -0.1700
Data Index: 5697716 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5260. Min Act: -0.1700
Data Index: 1429323 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5103. Min Act: -0.1700
Data Index: 5799182 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5260. Min Act: -0.1700
Data Index: 5579453 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5103. Min Act: -0.1700
Data Index: 7961341 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5103. Min Act: -0.1700
Data Index: 4353996 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5260. Min Act: -0.1700
Data Index: 7405468 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4947. Min Act: -0.1700
Data Index: 6741330 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4947. Min Act: -0.1700
Data Index: 569995 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4790. Min Act: -0.1700
Data Index: 2297964 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4947. Min Act: -0.1700
Data Index: 2772560 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4947. Min Act: -0.1700
Data Index: 2064829 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4790. Min Act: -0.1700
Data Index: 1601936 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4790. Min Act: -0.1700
Data Index: 3177653 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4790. Min Act: -0.1700
Data Index: 4736280 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4790. Min Act: -0.1700
Data Index: 3731405 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19