Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2126 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.6688. Min Act: -0.1700
Data Index: 1002098 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.5401. Min Act: -0.1700
Data Index: 1190046 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.5401. Min Act: -0.1700
Data Index: 7438562 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.5563. Min Act: -0.1700
Data Index: 1607519 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.5563. Min Act: -0.1699
Data Index: 4683973 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.5240. Min Act: -0.1700
Data Index: 177910 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.5078. Min Act: -0.1700
Data Index: 1086132 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.5078. Min Act: -0.1700
Data Index: 8061040 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.5078. Min Act: -0.1700
Data Index: 8084076 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.4916. Min Act: -0.1700
Data Index: 7054526 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.4916. Min Act: -0.1700
Data Index: 6981475 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.4916. Min Act: -0.1700
Data Index: 1965434 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.4753. Min Act: -0.1700
Data Index: 1015956 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.4916. Min Act: -0.1700
Data Index: 4490456 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.4753. Min Act: -0.1700
Data Index: 2168944 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.4591. Min Act: -0.1699
Data Index: 7235504 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.4266. Min Act: -0.1700
Data Index: 5095482 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.4266. Min Act: -0.1700
Data Index: 5351154 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.4266. Min Act: -0.1700
Data Index: 5336912 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6688. Min Range: -2.6688
Max Act: 2.4266. Min Act: -0.1700
Data Index: 5247721 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19