Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2057. Min Range: -8.2057
Max Act: 8.2057. Min Act: -0.1700
Data Index: 8237376 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2057. Min Range: -8.2057
Max Act: 8.1432. Min Act: -0.1700
Data Index: 7162341 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.8307. Min Act: -0.1700
Data Index: 5642823 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.8307. Min Act: -0.1700
Data Index: 8263345 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.7369. Min Act: -0.1700
Data Index: 4555217 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.4869. Min Act: -0.1700
Data Index: 8013113 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.4869. Min Act: -0.1700
Data Index: 5510333 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.4557. Min Act: -0.1700
Data Index: 3100390 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.4557. Min Act: -0.1700
Data Index: 3245032 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.4244. Min Act: -0.1700
Data Index: 5709007 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.3932. Min Act: -0.1700
Data Index: 8361960 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.3932. Min Act: -0.1700
Data Index: 8085195 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.3932. Min Act: -0.1700
Data Index: 106761 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.4244. Min Act: -0.1700
Data Index: 4276480 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.3932. Min Act: -0.1700
Data Index: 5432452 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.3932. Min Act: -0.1700
Data Index: 7630193 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.3619. Min Act: -0.1700
Data Index: 1063070 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.3619. Min Act: -0.1700
Data Index: 8237377 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.3619. Min Act: -0.1700
Data Index: 2656854 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2057. Min Range: -8.2057
Max Act: 7.3307. Min Act: -0.1700
Data Index: 725666 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19