Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2589 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.5877. Min Range: -9.5877
Max Act: 9.5877. Min Act: -0.1700
Data Index: 5542294 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5877. Min Range: -9.5877
Max Act: 9.1502. Min Act: -0.1700
Data Index: 6646674 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.9002. Min Act: -0.1700
Data Index: 2204644 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.9002. Min Act: -0.1700
Data Index: 5313031 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.9002. Min Act: -0.1700
Data Index: 5042679 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.8377. Min Act: -0.1700
Data Index: 3848083 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.7752. Min Act: -0.1700
Data Index: 5042680 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.7752. Min Act: -0.1700
Data Index: 7032895 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.7127. Min Act: -0.1700
Data Index: 7542764 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.7127. Min Act: -0.1700
Data Index: 2416485 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.7127. Min Act: -0.1700
Data Index: 5142133 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.6502. Min Act: -0.1700
Data Index: 4902694 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.6502. Min Act: -0.1700
Data Index: 7660908 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.6502. Min Act: -0.1700
Data Index: 2589310 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.5877. Min Act: -0.1700
Data Index: 5725876 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.5877. Min Act: -0.1700
Data Index: 3990699 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.5877. Min Act: -0.1700
Data Index: 2294569 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.5252. Min Act: -0.1700
Data Index: 7203905 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.5252. Min Act: -0.1700
Data Index: 4139130 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5877. Min Range: -9.5877
Max Act: 8.5252. Min Act: -0.1700
Data Index: 4139131 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19