Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.2486. Min Act: -0.1700
Data Index: 4833082 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.2486. Min Act: -0.1700
Data Index: 7274345 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.1549. Min Act: -0.1700
Data Index: 3413548 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.0299. Min Act: -0.1700
Data Index: 3195631 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.0611. Min Act: -0.1700
Data Index: 7850212 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2486. Min Range: -5.2486
Max Act: 5.0299. Min Act: -0.1700
Data Index: 1945335 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.9986. Min Act: -0.1700
Data Index: 7610155 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.9674. Min Act: -0.1700
Data Index: 1283780 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.9361. Min Act: -0.1700
Data Index: 7047425 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.9361. Min Act: -0.1700
Data Index: 19010 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.9361. Min Act: -0.1700
Data Index: 6774569 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.9049. Min Act: -0.1700
Data Index: 382235 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.9049. Min Act: -0.1700
Data Index: 3633973 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.8736. Min Act: -0.1700
Data Index: 4547781 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.8736. Min Act: -0.1700
Data Index: 1156307 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.8736. Min Act: -0.1700
Data Index: 6041371 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.8736. Min Act: -0.1700
Data Index: 1651930 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.8424. Min Act: -0.1700
Data Index: 6796493 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.8424. Min Act: -0.1700
Data Index: 3561839 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2486. Min Range: -5.2486
Max Act: 4.8424. Min Act: -0.1700
Data Index: 3539373 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19