Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.9235. Min Act: -0.1700
Data Index: 2170786 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.6110. Min Act: -0.1700
Data Index: 2633351 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.5172. Min Act: -0.1700
Data Index: 5880775 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.4235. Min Act: -0.1700
Data Index: 1299958 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.4235. Min Act: -0.1700
Data Index: 7304230 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.4235. Min Act: -0.1700
Data Index: 8781094 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.3922. Min Act: -0.1700
Data Index: 3903105 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.4235. Min Act: -0.1700
Data Index: 1112664 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.3922. Min Act: -0.1700
Data Index: 7466965 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.3610. Min Act: -0.1700
Data Index: 5910337 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.3297. Min Act: -0.1700
Data Index: 94603 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.3610. Min Act: -0.1700
Data Index: 3231174 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.3922. Min Act: -0.1700
Data Index: 1124316 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.2985. Min Act: -0.1700
Data Index: 3166129 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.3297. Min Act: -0.1700
Data Index: 7101311 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.3297. Min Act: -0.1700
Data Index: 7098910 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.2985. Min Act: -0.1700
Data Index: 7738351 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.2985. Min Act: -0.1700
Data Index: 1870032 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.2985. Min Act: -0.1700
Data Index: 3337909 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9235. Min Range: -5.9235
Max Act: 5.2985. Min Act: -0.1700
Data Index: 5527704 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19