Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3614 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.5139. Min Act: -0.1700
Data Index: 845332 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.4201. Min Act: -0.1700
Data Index: 845331 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2951. Min Act: -0.1700
Data Index: 4965123 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2951. Min Act: -0.1700
Data Index: 6111540 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2639. Min Act: -0.1700
Data Index: 2148505 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2639. Min Act: -0.1700
Data Index: 1928583 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2639. Min Act: -0.1700
Data Index: 5791434 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2326. Min Act: -0.1700
Data Index: 2852870 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2326. Min Act: -0.1700
Data Index: 8337707 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2014. Min Act: -0.1700
Data Index: 6649818 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2014. Min Act: -0.1700
Data Index: 3713379 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.1701. Min Act: -0.1700
Data Index: 3670645 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.1389. Min Act: -0.1700
Data Index: 3670646 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.1389. Min Act: -0.1700
Data Index: 6545062 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.1076. Min Act: -0.1700
Data Index: 3133113 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.1076. Min Act: -0.1700
Data Index: 7536607 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.0764. Min Act: -0.1700
Data Index: 8566586 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.1076. Min Act: -0.1700
Data Index: 3670647 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.0764. Min Act: -0.1700
Data Index: 5903329 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.0764. Min Act: -0.1700
Data Index: 5944143 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19