Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.5370. Min Act: -0.1700
Data Index: 8735668 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.5370. Min Act: -0.1700
Data Index: 1827897 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.4433. Min Act: -0.1700
Data Index: 6105662 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.3808. Min Act: -0.1700
Data Index: 2636641 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.2870. Min Act: -0.1700
Data Index: 2354689 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.3183. Min Act: -0.1700
Data Index: 8260218 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.2870. Min Act: -0.1700
Data Index: 8704434 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.3183. Min Act: -0.1700
Data Index: 5434221 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.2558. Min Act: -0.1700
Data Index: 6863092 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.1933. Min Act: -0.1700
Data Index: 6863094 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.2245. Min Act: -0.1700
Data Index: 7484161 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.1620. Min Act: -0.1700
Data Index: 5188142 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.1620. Min Act: -0.1700
Data Index: 1971909 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.1620. Min Act: -0.1700
Data Index: 4902286 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.1933. Min Act: -0.1700
Data Index: 2004059 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.1308. Min Act: -0.1700
Data Index: 2910959 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.0995. Min Act: -0.1700
Data Index: 613137 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.0995. Min Act: -0.1700
Data Index: 3686020 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.0683. Min Act: -0.1700
Data Index: 431346 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5370. Min Range: -7.5370
Max Act: 7.0058. Min Act: -0.1700
Data Index: 1965809 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19