Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2869 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.2820. Min Act: -0.1700
Data Index: 6721736 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.2506. Min Act: -0.1700
Data Index: 1677487 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.2349. Min Act: -0.1700
Data Index: 5445959 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.1248. Min Act: -0.1700
Data Index: 2902863 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.1563. Min Act: -0.1700
Data Index: 5230438 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.0775. Min Act: -0.1700
Data Index: 8656651 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.0933. Min Act: -0.1700
Data Index: 7733301 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.0775. Min Act: -0.1700
Data Index: 2186731 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.0775. Min Act: -0.1700
Data Index: 3602154 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.0302. Min Act: -0.1700
Data Index: 1044754 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.0302. Min Act: -0.1700
Data Index: 6910246 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.0617. Min Act: -0.1700
Data Index: 286015 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2820. Min Range: -3.2820
Max Act: 2.9828. Min Act: -0.1700
Data Index: 7332729 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.0460. Min Act: -0.1700
Data Index: 7363569 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.0144. Min Act: -0.1700
Data Index: 1702313 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2820. Min Range: -3.2820
Max Act: 2.9986. Min Act: -0.1700
Data Index: 7217009 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2820. Min Range: -3.2820
Max Act: 2.9986. Min Act: -0.1700
Data Index: 4224500 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2820. Min Range: -3.2820
Max Act: 2.9669. Min Act: -0.1700
Data Index: 5824120 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2820. Min Range: -3.2820
Max Act: 3.0144. Min Act: -0.1700
Data Index: 7128841 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2820. Min Range: -3.2820
Max Act: 2.9828. Min Act: -0.1700
Data Index: 4051466 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19