Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1040. Min Range: -2.1040
Max Act: 2.1040. Min Act: -0.1700
Data Index: 7318624 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1040. Min Range: -2.1040
Max Act: 2.0705. Min Act: -0.1700
Data Index: 7557975 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1040. Min Range: -2.1040
Max Act: 2.0705. Min Act: -0.1700
Data Index: 2066705 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1040. Min Range: -2.1040
Max Act: 2.0705. Min Act: -0.1687
Data Index: 3883496 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1040. Min Range: -2.1040
Max Act: 2.0200. Min Act: -0.1677
Data Index: 2144353 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1040. Min Range: -2.1040
Max Act: 2.0200. Min Act: -0.1700
Data Index: 4876393 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1040. Min Range: -2.1040
Max Act: 2.0031. Min Act: -0.1700
Data Index: 5366942 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1040. Min Range: -2.1040
Max Act: 2.0031. Min Act: -0.1700
Data Index: 3938215 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1040. Min Range: -2.1040
Max Act: 1.9862. Min Act: -0.1700
Data Index: 5362591 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1040. Min Range: -2.1040
Max Act: 2.0200. Min Act: -0.1700
Data Index: 4721415 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1040. Min Range: -2.1040
Max Act: 1.9862. Min Act: -0.1700
Data Index: 7453145 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1040. Min Range: -2.1040
Max Act: 1.9862. Min Act: -0.1700
Data Index: 4041977 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1040. Min Range: -2.1040
Max Act: 2.0031. Min Act: -0.1700
Data Index: 2772750 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1040. Min Range: -2.1040
Max Act: 1.9862. Min Act: -0.1697
Data Index: 5782753 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1040. Min Range: -2.1040
Max Act: 1.9862. Min Act: -0.1700
Data Index: 264757 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1040. Min Range: -2.1040
Max Act: 1.9693. Min Act: -0.1700
Data Index: 1424080 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1040. Min Range: -2.1040
Max Act: 1.9693. Min Act: -0.1700
Data Index: 4920511 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1040. Min Range: -2.1040
Max Act: 1.9693. Min Act: -0.1700
Data Index: 1326152 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1040. Min Range: -2.1040
Max Act: 1.9608. Min Act: -0.1700
Data Index: 6084039 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1040. Min Range: -2.1040
Max Act: 1.9608. Min Act: -0.1700
Data Index: 3516602 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19