Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3708. Min Range: -8.3708
Max Act: 8.3708. Min Act: -0.1700
Data Index: 1366452 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3708. Min Range: -8.3708
Max Act: 8.1208. Min Act: -0.1700
Data Index: 2630405 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.9958. Min Act: -0.1700
Data Index: 5466263 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.9333. Min Act: -0.1700
Data Index: 3720401 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.8708. Min Act: -0.1700
Data Index: 5661889 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.8083. Min Act: -0.1700
Data Index: 5666713 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.8708. Min Act: -0.1700
Data Index: 1622707 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.8083. Min Act: -0.1700
Data Index: 8264140 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.8083. Min Act: -0.1700
Data Index: 4011586 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.7458. Min Act: -0.1700
Data Index: 4590561 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.7458. Min Act: -0.1700
Data Index: 4473061 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.7458. Min Act: -0.1700
Data Index: 1842268 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.6833. Min Act: -0.1700
Data Index: 7454945 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.7458. Min Act: -0.1700
Data Index: 398731 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.7458. Min Act: -0.1700
Data Index: 2412090 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.8083. Min Act: -0.1700
Data Index: 3783983 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.6833. Min Act: -0.1700
Data Index: 7369098 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.6833. Min Act: -0.1700
Data Index: 6715786 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.6833. Min Act: -0.1700
Data Index: 5794370 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3708. Min Range: -8.3708
Max Act: 7.6833. Min Act: -0.1700
Data Index: 1149081 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19