Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1130. Min Range: -5.1130
Max Act: 5.1130. Min Act: -0.1700
Data Index: 340093 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1130. Min Range: -5.1130
Max Act: 5.0193. Min Act: -0.1700
Data Index: 3859180 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9880. Min Act: -0.1700
Data Index: 7820663 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9568. Min Act: -0.1700
Data Index: 1142245 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9255. Min Act: -0.1700
Data Index: 4441621 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.9255. Min Act: -0.1700
Data Index: 145906 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.8943. Min Act: -0.1700
Data Index: 3901767 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.8943. Min Act: -0.1700
Data Index: 8687216 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.8630. Min Act: -0.1700
Data Index: 6128749 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.8318. Min Act: -0.1700
Data Index: 3949286 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.8005. Min Act: -0.1700
Data Index: 1262230 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.8005. Min Act: -0.1700
Data Index: 1348213 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.7380. Min Act: -0.1700
Data Index: 7222347 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.7380. Min Act: -0.1700
Data Index: 7490386 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.7380. Min Act: -0.1700
Data Index: 3912683 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.7068. Min Act: -0.1700
Data Index: 5282160 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.7068. Min Act: -0.1700
Data Index: 450899 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.7380. Min Act: -0.1700
Data Index: 1962967 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.6755. Min Act: -0.1700
Data Index: 5387677 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1130. Min Range: -5.1130
Max Act: 4.6755. Min Act: -0.1700
Data Index: 5880127 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19