Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2134 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.1223. Min Range: -4.1223
Max Act: 4.1223. Min Act: -0.1700
Data Index: 8118104 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.9504. Min Act: -0.1700
Data Index: 2985168 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.9504. Min Act: -0.1700
Data Index: 469592 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.8722. Min Act: -0.1700
Data Index: 5379869 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.7940. Min Act: -0.1700
Data Index: 8010212 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.8097. Min Act: -0.1700
Data Index: 1368796 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.7784. Min Act: -0.1700
Data Index: 4088114 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.7784. Min Act: -0.1700
Data Index: 3195311 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.7784. Min Act: -0.1700
Data Index: 1244170 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.7471. Min Act: -0.1700
Data Index: 4322628 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.7471. Min Act: -0.1700
Data Index: 4098906 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.7471. Min Act: -0.1700
Data Index: 1667393 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.7158. Min Act: -0.1700
Data Index: 8438861 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.6845. Min Act: -0.1700
Data Index: 1642988 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.7002. Min Act: -0.1700
Data Index: 3963565 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.7002. Min Act: -0.1700
Data Index: 3612520 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.6689. Min Act: -0.1700
Data Index: 6081967 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.7002. Min Act: -0.1700
Data Index: 1551008 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.6689. Min Act: -0.1700
Data Index: 1200709 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1223. Min Range: -4.1223
Max Act: 3.6845. Min Act: -0.1700
Data Index: 321994 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19