Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2013 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1180. Min Range: -5.1180
Max Act: 5.1180. Min Act: -0.1700
Data Index: 2917269 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1180. Min Range: -5.1180
Max Act: 5.0242. Min Act: -0.1700
Data Index: 3201675 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.8992. Min Act: -0.1700
Data Index: 2104634 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.7430. Min Act: -0.1700
Data Index: 182523 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.7117. Min Act: -0.1700
Data Index: 5296146 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.6805. Min Act: -0.1700
Data Index: 8783544 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.6180. Min Act: -0.1700
Data Index: 3396395 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.6492. Min Act: -0.1700
Data Index: 1163759 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.5867. Min Act: -0.1700
Data Index: 5368702 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.5867. Min Act: -0.1700
Data Index: 5184343 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.5555. Min Act: -0.1700
Data Index: 5648015 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.5555. Min Act: -0.1700
Data Index: 1652474 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.4930. Min Act: -0.1700
Data Index: 2233042 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.5242. Min Act: -0.1700
Data Index: 5325188 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.5242. Min Act: -0.1700
Data Index: 3411622 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.4930. Min Act: -0.1700
Data Index: 901545 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.4930. Min Act: -0.1700
Data Index: 6060513 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.5242. Min Act: -0.1700
Data Index: 7551825 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.5242. Min Act: -0.1700
Data Index: 3916573 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1180. Min Range: -5.1180
Max Act: 4.4930. Min Act: -0.1700
Data Index: 5477129 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19