Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.4323. Min Act: -0.1700
Data Index: 1979500 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.4323. Min Act: -0.1700
Data Index: 2440667 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.3385. Min Act: -0.1700
Data Index: 1080640 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.3385. Min Act: -0.1700
Data Index: 5350125 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.2760. Min Act: -0.1700
Data Index: 3908286 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.3073. Min Act: -0.1700
Data Index: 7984528 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.3073. Min Act: -0.1700
Data Index: 5913239 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.2760. Min Act: -0.1700
Data Index: 5835887 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.2760. Min Act: -0.1700
Data Index: 2253327 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.2448. Min Act: -0.1700
Data Index: 241702 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.2760. Min Act: -0.1700
Data Index: 2448422 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.2135. Min Act: -0.1700
Data Index: 1262928 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.2448. Min Act: -0.1700
Data Index: 7502087 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.2448. Min Act: -0.1700
Data Index: 5847408 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.2135. Min Act: -0.1700
Data Index: 5817902 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.2135. Min Act: -0.1700
Data Index: 8043609 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.1823. Min Act: -0.1700
Data Index: 7207914 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.1823. Min Act: -0.1700
Data Index: 3828932 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.1823. Min Act: -0.1700
Data Index: 5680239 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4323. Min Range: -7.4323
Max Act: 7.1823. Min Act: -0.1700
Data Index: 5333966 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19