Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2866. Min Range: -7.2866
Max Act: 7.2866. Min Act: -0.1700
Data Index: 5834748 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2866. Min Range: -7.2866
Max Act: 7.1616. Min Act: -0.1700
Data Index: 2736980 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2866. Min Range: -7.2866
Max Act: 7.0991. Min Act: -0.1700
Data Index: 4631773 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2866. Min Range: -7.2866
Max Act: 7.0366. Min Act: -0.1700
Data Index: 6260983 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.9741. Min Act: -0.1700
Data Index: 2447601 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.7866. Min Act: -0.1700
Data Index: 2116885 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.7554. Min Act: -0.1700
Data Index: 4075181 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.7241. Min Act: -0.1700
Data Index: 3000800 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.6929. Min Act: -0.1700
Data Index: 7406018 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.6929. Min Act: -0.1700
Data Index: 3257769 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.6616. Min Act: -0.1700
Data Index: 25238 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.6616. Min Act: -0.1700
Data Index: 4861017 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.5991. Min Act: -0.1700
Data Index: 1284556 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.6304. Min Act: -0.1700
Data Index: 5959170 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.5679. Min Act: -0.1700
Data Index: 7405590 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.5366. Min Act: -0.1700
Data Index: 4242532 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.5366. Min Act: -0.1700
Data Index: 8073784 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.5054. Min Act: -0.1700
Data Index: 1325856 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.5054. Min Act: -0.1700
Data Index: 5549273 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2866. Min Range: -7.2866
Max Act: 6.5054. Min Act: -0.1700
Data Index: 1897462 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19