Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2366. Min Range: -7.2366
Max Act: 7.2366. Min Act: -0.1700
Data Index: 2130166 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2366. Min Range: -7.2366
Max Act: 7.1116. Min Act: -0.1700
Data Index: 6815787 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2366. Min Range: -7.2366
Max Act: 7.0803. Min Act: -0.1700
Data Index: 7927251 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.9866. Min Act: -0.1700
Data Index: 6230777 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.9553. Min Act: -0.1700
Data Index: 6916008 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.9553. Min Act: -0.1700
Data Index: 3195066 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.9241. Min Act: -0.1700
Data Index: 2477541 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.9241. Min Act: -0.1700
Data Index: 2157743 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.8928. Min Act: -0.1700
Data Index: 1773453 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.8928. Min Act: -0.1700
Data Index: 3119264 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.8928. Min Act: -0.1700
Data Index: 1894281 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.8928. Min Act: -0.1700
Data Index: 1521917 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.8616. Min Act: -0.1700
Data Index: 3011922 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.8928. Min Act: -0.1700
Data Index: 8337725 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.8616. Min Act: -0.1700
Data Index: 7707901 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.8616. Min Act: -0.1700
Data Index: 830303 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.8928. Min Act: -0.1700
Data Index: 7238593 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.8303. Min Act: -0.1700
Data Index: 7589326 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.7991. Min Act: -0.1700
Data Index: 6200798 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2366. Min Range: -7.2366
Max Act: 6.8303. Min Act: -0.1700
Data Index: 8213943 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19