Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1548. Min Range: -5.1548
Max Act: 5.1548. Min Act: -0.1700
Data Index: 3537393 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1548. Min Range: -5.1548
Max Act: 5.0611. Min Act: -0.1700
Data Index: 1568105 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1548. Min Range: -5.1548
Max Act: 5.0611. Min Act: -0.1700
Data Index: 4596187 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1548. Min Range: -5.1548
Max Act: 5.0298. Min Act: -0.1700
Data Index: 1609425 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9986. Min Act: -0.1700
Data Index: 4172764 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9986. Min Act: -0.1700
Data Index: 621980 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9986. Min Act: -0.1700
Data Index: 1499004 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9986. Min Act: -0.1700
Data Index: 7883429 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9673. Min Act: -0.1700
Data Index: 8265431 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9361. Min Act: -0.1700
Data Index: 1215588 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9673. Min Act: -0.1700
Data Index: 1078264 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9986. Min Act: -0.1700
Data Index: 1449993 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9673. Min Act: -0.1700
Data Index: 8360182 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9361. Min Act: -0.1700
Data Index: 161846 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9048. Min Act: -0.1700
Data Index: 98411 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9048. Min Act: -0.1700
Data Index: 476681 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.8736. Min Act: -0.1700
Data Index: 3906094 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.9048. Min Act: -0.1700
Data Index: 3266541 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.8736. Min Act: -0.1700
Data Index: 6748498 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1548. Min Range: -5.1548
Max Act: 4.8736. Min Act: -0.1700
Data Index: 1987229 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19