Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3377 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.8994. Min Act: -0.1700
Data Index: 1553174 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.8994. Min Act: -0.1700
Data Index: 8562879 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.8994. Min Act: -0.1700
Data Index: 3833786 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.8057. Min Act: -0.1700
Data Index: 7090707 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.7744. Min Act: -0.1700
Data Index: 1909002 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.7744. Min Act: -0.1700
Data Index: 5303698 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.7744. Min Act: -0.1700
Data Index: 1553172 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.6807. Min Act: -0.1700
Data Index: 1148954 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.7119. Min Act: -0.1700
Data Index: 8572654 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.7119. Min Act: -0.1700
Data Index: 1437357 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.6807. Min Act: -0.1700
Data Index: 4567283 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.6494. Min Act: -0.1700
Data Index: 1553169 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.6182. Min Act: -0.1700
Data Index: 4852313 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.6494. Min Act: -0.1700
Data Index: 5479026 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.6807. Min Act: -0.1700
Data Index: 3651522 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.6182. Min Act: -0.1700
Data Index: 7090713 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.5557. Min Act: -0.1700
Data Index: 7204664 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.5244. Min Act: -0.1700
Data Index: 1248390 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.5244. Min Act: -0.1700
Data Index: 7090704 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8994. Min Range: -5.8994
Max Act: 5.4932. Min Act: -0.1700
Data Index: 5142502 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19