Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2198 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2361. Min Range: -6.2361
Max Act: 6.2361. Min Act: -0.1700
Data Index: 1863504 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2361. Min Range: -6.2361
Max Act: 6.1736. Min Act: -0.1700
Data Index: 1795566 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2361. Min Range: -6.2361
Max Act: 6.1111. Min Act: -0.1700
Data Index: 1975522 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2361. Min Range: -6.2361
Max Act: 6.1111. Min Act: -0.1700
Data Index: 5789568 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2361. Min Range: -6.2361
Max Act: 6.0174. Min Act: -0.1700
Data Index: 5425146 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2361. Min Range: -6.2361
Max Act: 6.0174. Min Act: -0.1700
Data Index: 6901535 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.9861. Min Act: -0.1700
Data Index: 4085914 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.9861. Min Act: -0.1700
Data Index: 2985199 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.9861. Min Act: -0.1700
Data Index: 4784815 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.9549. Min Act: -0.1700
Data Index: 4466830 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.9549. Min Act: -0.1700
Data Index: 4279016 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.9549. Min Act: -0.1700
Data Index: 4858926 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.9236. Min Act: -0.1700
Data Index: 8335635 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.9236. Min Act: -0.1700
Data Index: 7592103 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.9236. Min Act: -0.1700
Data Index: 4459261 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.8611. Min Act: -0.1700
Data Index: 1566279 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.8924. Min Act: -0.1700
Data Index: 4420493 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.8611. Min Act: -0.1700
Data Index: 6726449 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.8611. Min Act: -0.1700
Data Index: 1122332 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2361. Min Range: -6.2361
Max Act: 5.8611. Min Act: -0.1700
Data Index: 5245884 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19