Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 925 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.8917. Min Act: -0.1700
Data Index: 2600985 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.8604. Min Act: -0.1700
Data Index: 7883241 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.8917. Min Act: -0.1700
Data Index: 516218 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7667. Min Act: -0.1700
Data Index: 6851926 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7979. Min Act: -0.1700
Data Index: 3172867 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7667. Min Act: -0.1700
Data Index: 897444 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7979. Min Act: -0.1700
Data Index: 7761688 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7979. Min Act: -0.1700
Data Index: 862226 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7979. Min Act: -0.1700
Data Index: 274032 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7979. Min Act: -0.1700
Data Index: 7408967 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7667. Min Act: -0.1700
Data Index: 7678133 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7979. Min Act: -0.1700
Data Index: 7911975 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7354. Min Act: -0.1700
Data Index: 6585718 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7354. Min Act: -0.1700
Data Index: 891792 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7354. Min Act: -0.1700
Data Index: 2484318 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7042. Min Act: -0.1700
Data Index: 2014600 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7354. Min Act: -0.1700
Data Index: 4412016 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.7354. Min Act: -0.1700
Data Index: 2318518 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.6729. Min Act: -0.1700
Data Index: 7435142 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8917. Min Range: -7.8917
Max Act: 7.6417. Min Act: -0.1700
Data Index: 1569186 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19