Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.8037. Min Act: -0.1700
Data Index: 651262 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.8350. Min Act: -0.1700
Data Index: 5824519 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.8037. Min Act: -0.1700
Data Index: 5523439 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.8037. Min Act: -0.1700
Data Index: 2680051 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.7412. Min Act: -0.1700
Data Index: 3544503 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.6787. Min Act: -0.1700
Data Index: 4279611 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.6475. Min Act: -0.1700
Data Index: 3938799 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.6475. Min Act: -0.1700
Data Index: 8306758 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.5850. Min Act: -0.1700
Data Index: 3732360 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.5537. Min Act: -0.1700
Data Index: 7232057 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.5850. Min Act: -0.1700
Data Index: 3381650 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.5850. Min Act: -0.1700
Data Index: 1356954 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.5537. Min Act: -0.1700
Data Index: 4430983 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.5537. Min Act: -0.1700
Data Index: 5159269 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.4912. Min Act: -0.1700
Data Index: 110975 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.4912. Min Act: -0.1700
Data Index: 6312447 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.4600. Min Act: -0.1700
Data Index: 656653 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.4287. Min Act: -0.1700
Data Index: 4635666 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.4287. Min Act: -0.1700
Data Index: 4676390 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8350. Min Range: -7.8350
Max Act: 7.3975. Min Act: -0.1700
Data Index: 5754656 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19