Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.6765. Min Act: -0.1700
Data Index: 5767396 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.6765. Min Act: -0.1700
Data Index: 2650992 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.6453. Min Act: -0.1700
Data Index: 735483 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.5828. Min Act: -0.1700
Data Index: 7555558 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.5203. Min Act: -0.1700
Data Index: 8693129 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.5203. Min Act: -0.1699
Data Index: 3103546 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.4265. Min Act: -0.1700
Data Index: 526187 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.4265. Min Act: -0.1700
Data Index: 5861566 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.4265. Min Act: -0.1700
Data Index: 8060160 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.4265. Min Act: -0.1700
Data Index: 8535334 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.3953. Min Act: -0.1700
Data Index: 7731939 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.3953. Min Act: -0.1700
Data Index: 1640579 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.3953. Min Act: -0.1700
Data Index: 6328115 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.3953. Min Act: -0.1700
Data Index: 1497370 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.3953. Min Act: -0.1700
Data Index: 5022394 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.3640. Min Act: -0.1700
Data Index: 5679858 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.3640. Min Act: -0.1700
Data Index: 7399859 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.3640. Min Act: -0.1700
Data Index: 5256000 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.3640. Min Act: -0.1700
Data Index: 8387167 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6765. Min Range: -5.6765
Max Act: 5.3640. Min Act: -0.1700
Data Index: 6475841 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19