Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6137 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.3549. Min Act: -0.1700
Data Index: 5666109 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.2924. Min Act: -0.1700
Data Index: 855140 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.2924. Min Act: -0.1700
Data Index: 4916930 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.2611. Min Act: -0.1700
Data Index: 5620283 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.2924. Min Act: -0.1700
Data Index: 2017624 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.2299. Min Act: -0.1700
Data Index: 516487 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.1986. Min Act: -0.1700
Data Index: 5429489 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.1986. Min Act: -0.1700
Data Index: 139023 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.1674. Min Act: -0.1700
Data Index: 338641 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.1361. Min Act: -0.1700
Data Index: 4473707 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.1049. Min Act: -0.1700
Data Index: 7119512 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.0736. Min Act: -0.1700
Data Index: 4840765 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.0736. Min Act: -0.1700
Data Index: 6845805 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.0736. Min Act: -0.1700
Data Index: 6180674 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.0736. Min Act: -0.1700
Data Index: 155082 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.0736. Min Act: -0.1700
Data Index: 1572140 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.0424. Min Act: -0.1700
Data Index: 3951155 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.0424. Min Act: -0.1700
Data Index: 4261962 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.0424. Min Act: -0.1700
Data Index: 1547393 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3549. Min Range: -6.3549
Max Act: 6.0111. Min Act: -0.1700
Data Index: 1408334 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19