Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1033 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.3561. Min Act: -0.1700
Data Index: 2053684 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.2936. Min Act: -0.1700
Data Index: 8261840 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.2936. Min Act: -0.1700
Data Index: 7301788 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.2624. Min Act: -0.1700
Data Index: 12545 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1999. Min Act: -0.1700
Data Index: 2968305 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1686. Min Act: -0.1700
Data Index: 6321018 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1686. Min Act: -0.1700
Data Index: 1669231 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1061. Min Act: -0.1700
Data Index: 763621 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1374. Min Act: -0.1700
Data Index: 1795397 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1061. Min Act: -0.1700
Data Index: 5463619 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1374. Min Act: -0.1700
Data Index: 6618366 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1061. Min Act: -0.1700
Data Index: 7816686 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1061. Min Act: -0.1700
Data Index: 4664147 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1061. Min Act: -0.1700
Data Index: 2790955 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1061. Min Act: -0.1700
Data Index: 4556712 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.0749. Min Act: -0.1700
Data Index: 8431790 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.0749. Min Act: -0.1700
Data Index: 6321019 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.0749. Min Act: -0.1700
Data Index: 2790688 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.0749. Min Act: -0.1700
Data Index: 8691106 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.0436. Min Act: -0.1700
Data Index: 6276418 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19