Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1732. Min Range: -5.1732
Max Act: 5.1732. Min Act: -0.1700
Data Index: 5870469 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1732. Min Range: -5.1732
Max Act: 5.1420. Min Act: -0.1700
Data Index: 3320954 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1732. Min Range: -5.1732
Max Act: 5.0795. Min Act: -0.1700
Data Index: 1819814 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1732. Min Range: -5.1732
Max Act: 5.0170. Min Act: -0.1700
Data Index: 663877 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.9545. Min Act: -0.1700
Data Index: 4942096 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.9232. Min Act: -0.1700
Data Index: 616710 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.8607. Min Act: -0.1700
Data Index: 7905540 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.8607. Min Act: -0.1700
Data Index: 7983890 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.8295. Min Act: -0.1700
Data Index: 4089517 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7982. Min Act: -0.1700
Data Index: 1844464 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7982. Min Act: -0.1700
Data Index: 1926022 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7982. Min Act: -0.1700
Data Index: 8539061 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7670. Min Act: -0.1700
Data Index: 8280142 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7045. Min Act: -0.1700
Data Index: 5251323 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7357. Min Act: -0.1700
Data Index: 3473291 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7045. Min Act: -0.1700
Data Index: 6014827 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7045. Min Act: -0.1700
Data Index: 614871 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7045. Min Act: -0.1700
Data Index: 4032388 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.6732. Min Act: -0.1700
Data Index: 2265124 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.6732. Min Act: -0.1700
Data Index: 6546182 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19