Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2749 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2949. Min Range: -7.2949
Max Act: 7.2949. Min Act: -0.1700
Data Index: 4021510 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2949. Min Range: -7.2949
Max Act: 7.2324. Min Act: -0.1700
Data Index: 6894836 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2949. Min Range: -7.2949
Max Act: 7.1387. Min Act: -0.1700
Data Index: 7229867 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2949. Min Range: -7.2949
Max Act: 7.2324. Min Act: -0.1700
Data Index: 5663679 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2949. Min Range: -7.2949
Max Act: 7.2012. Min Act: -0.1700
Data Index: 839169 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2949. Min Range: -7.2949
Max Act: 7.1699. Min Act: -0.1700
Data Index: 8124067 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2949. Min Range: -7.2949
Max Act: 7.0762. Min Act: -0.1700
Data Index: 8196036 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2949. Min Range: -7.2949
Max Act: 7.0762. Min Act: -0.1700
Data Index: 53704 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2949. Min Range: -7.2949
Max Act: 7.0137. Min Act: -0.1700
Data Index: 2707484 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2949. Min Range: -7.2949
Max Act: 7.0137. Min Act: -0.1700
Data Index: 1111355 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2949. Min Range: -7.2949
Max Act: 6.9512. Min Act: -0.1700
Data Index: 1431289 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2949. Min Range: -7.2949
Max Act: 6.9199. Min Act: -0.1700
Data Index: 2275572 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2949. Min Range: -7.2949
Max Act: 6.9199. Min Act: -0.1700
Data Index: 1965742 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2949. Min Range: -7.2949
Max Act: 6.8574. Min Act: -0.1700
Data Index: 3604082 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2949. Min Range: -7.2949
Max Act: 6.8262. Min Act: -0.1700
Data Index: 1756934 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2949. Min Range: -7.2949
Max Act: 6.8262. Min Act: -0.1700
Data Index: 3474638 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2949. Min Range: -7.2949
Max Act: 6.8574. Min Act: -0.1700
Data Index: 8109912 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2949. Min Range: -7.2949
Max Act: 6.7637. Min Act: -0.1700
Data Index: 3888357 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2949. Min Range: -7.2949
Max Act: 6.7324. Min Act: -0.1700
Data Index: 5160552 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2949. Min Range: -7.2949
Max Act: 6.7012. Min Act: -0.1700
Data Index: 12056 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19