Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6340 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.4323. Min Act: -0.1700
Data Index: 3047461 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.4010. Min Act: -0.1700
Data Index: 2237770 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.3698. Min Act: -0.1700
Data Index: 1024668 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.3385. Min Act: -0.1700
Data Index: 8220636 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.2760. Min Act: -0.1700
Data Index: 295615 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.2135. Min Act: -0.1700
Data Index: 2969909 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.2135. Min Act: -0.1700
Data Index: 6335597 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1198. Min Act: -0.1700
Data Index: 843371 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1510. Min Act: -0.1700
Data Index: 50098 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1510. Min Act: -0.1700
Data Index: 2038409 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1510. Min Act: -0.1700
Data Index: 6562526 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1510. Min Act: -0.1700
Data Index: 642590 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1198. Min Act: -0.1700
Data Index: 4141654 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1510. Min Act: -0.1700
Data Index: 406212 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1510. Min Act: -0.1700
Data Index: 642589 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1198. Min Act: -0.1700
Data Index: 1961326 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1198. Min Act: -0.1700
Data Index: 7884750 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1198. Min Act: -0.1700
Data Index: 3528496 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.1198. Min Act: -0.1700
Data Index: 1445478 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4323. Min Range: -5.4323
Max Act: 5.0885. Min Act: -0.1700
Data Index: 5871614 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19