Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2401. Min Range: -9.2401
Max Act: 9.2401. Min Act: -0.1700
Data Index: 6405832 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.9276. Min Act: -0.1700
Data Index: 6150568 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.9901. Min Act: -0.1700
Data Index: 6334970 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.9276. Min Act: -0.1700
Data Index: 2264363 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.8651. Min Act: -0.1700
Data Index: 8567247 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.8651. Min Act: -0.1700
Data Index: 8142986 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.8026. Min Act: -0.1700
Data Index: 6736783 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.7401. Min Act: -0.1700
Data Index: 2425132 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.7401. Min Act: -0.1700
Data Index: 7029655 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.7401. Min Act: -0.1700
Data Index: 7114333 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.7401. Min Act: -0.1700
Data Index: 674175 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.7401. Min Act: -0.1700
Data Index: 3430689 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.6776. Min Act: -0.1700
Data Index: 4036405 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.6776. Min Act: -0.1700
Data Index: 4274330 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.6776. Min Act: -0.1700
Data Index: 8190155 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.6776. Min Act: -0.1700
Data Index: 8212289 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.6776. Min Act: -0.1700
Data Index: 3336219 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.6776. Min Act: -0.1700
Data Index: 3795822 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.6151. Min Act: -0.1700
Data Index: 1257810 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2401. Min Range: -9.2401
Max Act: 8.6151. Min Act: -0.1700
Data Index: 5130930 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19