Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.8213. Min Act: -0.1700
Data Index: 2170237 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.7736. Min Act: -0.1700
Data Index: 706490 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.7576. Min Act: -0.1700
Data Index: 4853084 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.7416. Min Act: -0.1700
Data Index: 4198999 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.7416. Min Act: -0.1700
Data Index: 836405 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.7257. Min Act: -0.1700
Data Index: 7943092 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.7257. Min Act: -0.1700
Data Index: 4899943 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.7257. Min Act: -0.1700
Data Index: 5026245 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.7097. Min Act: -0.1700
Data Index: 4448472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.7097. Min Act: -0.1700
Data Index: 2223825 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.6937. Min Act: -0.1700
Data Index: 5066543 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.6937. Min Act: -0.1700
Data Index: 6427661 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.6937. Min Act: -0.1700
Data Index: 3638748 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.6937. Min Act: -0.1700
Data Index: 4520782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.6777. Min Act: -0.1700
Data Index: 1615674 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.6777. Min Act: -0.1700
Data Index: 6322676 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.6777. Min Act: -0.1700
Data Index: 1209585 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.6777. Min Act: -0.1700
Data Index: 3101827 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.6937. Min Act: -0.1700
Data Index: 7251724 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8213. Min Range: -2.8213
Max Act: 2.6616. Min Act: -0.1700
Data Index: 3870932 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19