Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3708 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.7243. Min Act: -0.1700
Data Index: 7173072 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.6930. Min Act: -0.1700
Data Index: 5145651 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.5993. Min Act: -0.1700
Data Index: 4357252 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.5680. Min Act: -0.1700
Data Index: 985181 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.5368. Min Act: -0.1700
Data Index: 6466531 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.4430. Min Act: -0.1700
Data Index: 1714916 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.4118. Min Act: -0.1700
Data Index: 8184609 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.4118. Min Act: -0.1700
Data Index: 685211 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.4118. Min Act: -0.1700
Data Index: 3318002 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.3805. Min Act: -0.1700
Data Index: 874272 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.3805. Min Act: -0.1700
Data Index: 4330824 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.3805. Min Act: -0.1700
Data Index: 8328098 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.3805. Min Act: -0.1700
Data Index: 4553481 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.3493. Min Act: -0.1700
Data Index: 6466532 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.3493. Min Act: -0.1700
Data Index: 728852 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.3180. Min Act: -0.1700
Data Index: 853702 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.3180. Min Act: -0.1700
Data Index: 6216314 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.3180. Min Act: -0.1700
Data Index: 4067516 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.2868. Min Act: -0.1700
Data Index: 8661581 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7243. Min Range: -4.7243
Max Act: 4.3180. Min Act: -0.1700
Data Index: 7103126 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19