Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5647 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.2765. Min Act: -0.1700
Data Index: 6638393 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1202. Min Act: -0.1700
Data Index: 7280590 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1202. Min Act: -0.1700
Data Index: 7452163 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0890. Min Act: -0.1700
Data Index: 6630857 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0890. Min Act: -0.1700
Data Index: 4033343 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0890. Min Act: -0.1700
Data Index: 2890226 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0890. Min Act: -0.1700
Data Index: 7474605 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0577. Min Act: -0.1700
Data Index: 4772654 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0577. Min Act: -0.1700
Data Index: 4855585 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0577. Min Act: -0.1700
Data Index: 1642744 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0577. Min Act: -0.1700
Data Index: 7597351 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0577. Min Act: -0.1700
Data Index: 6911477 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0577. Min Act: -0.1700
Data Index: 6863567 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0577. Min Act: -0.1700
Data Index: 2323919 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0890. Min Act: -0.1700
Data Index: 1576365 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0577. Min Act: -0.1700
Data Index: 6440417 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0265. Min Act: -0.1700
Data Index: 987817 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0265. Min Act: -0.1700
Data Index: 1588082 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0265. Min Act: -0.1700
Data Index: 1206186 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0265. Min Act: -0.1700
Data Index: 4759519 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19