Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2069 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.4608. Min Act: -0.1700
Data Index: 1380175 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.4608. Min Act: -0.1700
Data Index: 3436836 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.4296. Min Act: -0.1700
Data Index: 1044365 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3983. Min Act: -0.1700
Data Index: 6844041 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3671. Min Act: -0.1700
Data Index: 8574218 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3671. Min Act: -0.1700
Data Index: 918892 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3358. Min Act: -0.1700
Data Index: 5600944 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3358. Min Act: -0.1700
Data Index: 550167 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3358. Min Act: -0.1700
Data Index: 8740813 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3358. Min Act: -0.1700
Data Index: 1106906 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3358. Min Act: -0.1700
Data Index: 7856268 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3046. Min Act: -0.1700
Data Index: 2075804 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3046. Min Act: -0.1700
Data Index: 7993075 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3046. Min Act: -0.1700
Data Index: 1281623 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.3046. Min Act: -0.1699
Data Index: 5123654 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.2733. Min Act: -0.1700
Data Index: 5250920 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.2733. Min Act: -0.1700
Data Index: 6501527 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.2733. Min Act: -0.1700
Data Index: 454434 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.2733. Min Act: -0.1700
Data Index: 5498257 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4608. Min Range: -5.4608
Max Act: 5.2421. Min Act: -0.1700
Data Index: 3663782 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19