Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1296 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3747. Min Range: -7.3747
Max Act: 7.3747. Min Act: -0.1700
Data Index: 296802 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.8435. Min Act: -0.1700
Data Index: 4503987 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.7185. Min Act: -0.1700
Data Index: 2900999 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.6247. Min Act: -0.1700
Data Index: 2949882 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.5935. Min Act: -0.1700
Data Index: 2975914 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.4997. Min Act: -0.1700
Data Index: 4029074 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.4997. Min Act: -0.1700
Data Index: 5345511 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.4997. Min Act: -0.1700
Data Index: 686677 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.4685. Min Act: -0.1700
Data Index: 1366880 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.4685. Min Act: -0.1700
Data Index: 7599162 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.3747. Min Act: -0.1700
Data Index: 1351699 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.3435. Min Act: -0.1700
Data Index: 6485391 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.3435. Min Act: -0.1700
Data Index: 1687928 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.3435. Min Act: -0.1700
Data Index: 1020670 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.3435. Min Act: -0.1700
Data Index: 7630916 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.3122. Min Act: -0.1700
Data Index: 3957125 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.3122. Min Act: -0.1700
Data Index: 2110062 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.2497. Min Act: -0.1700
Data Index: 2476535 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.2185. Min Act: -0.1700
Data Index: 5593657 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.2185. Min Act: -0.1700
Data Index: 2260873 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19