Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.7132. Min Act: -0.1700
Data Index: 997595 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.6507. Min Act: -0.1700
Data Index: 2707744 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.5570. Min Act: -0.1700
Data Index: 3800040 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.5570. Min Act: -0.1700
Data Index: 3077171 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.4945. Min Act: -0.1700
Data Index: 4789750 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.4632. Min Act: -0.1700
Data Index: 7096275 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.4632. Min Act: -0.1700
Data Index: 7923009 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.4320. Min Act: -0.1700
Data Index: 7887583 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.4320. Min Act: -0.1700
Data Index: 1993794 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.4320. Min Act: -0.1700
Data Index: 3974706 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.4320. Min Act: -0.1700
Data Index: 1502685 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.3695. Min Act: -0.1700
Data Index: 1329937 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.3382. Min Act: -0.1700
Data Index: 1041269 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.3382. Min Act: -0.1700
Data Index: 4005626 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.3382. Min Act: -0.1700
Data Index: 2774605 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.3070. Min Act: -0.1700
Data Index: 7782603 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.3070. Min Act: -0.1700
Data Index: 6594694 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.3382. Min Act: -0.1700
Data Index: 6002815 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.3070. Min Act: -0.1700
Data Index: 3204019 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7132. Min Range: -5.7132
Max Act: 5.2757. Min Act: -0.1700
Data Index: 805884 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19