Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4538 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.7709. Min Act: -0.1700
Data Index: 4721429 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.7397. Min Act: -0.1700
Data Index: 5119030 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6458. Min Act: -0.1700
Data Index: 2643834 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5988. Min Act: -0.1700
Data Index: 3317264 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5988. Min Act: -0.1700
Data Index: 2343303 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5988. Min Act: -0.1700
Data Index: 5764758 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5988. Min Act: -0.1700
Data Index: 2673725 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5988. Min Act: -0.1700
Data Index: 6383332 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5832. Min Act: -0.1700
Data Index: 6457944 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5675. Min Act: -0.1700
Data Index: 7276191 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5362. Min Act: -0.1700
Data Index: 5497756 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5049. Min Act: -0.1700
Data Index: 4834250 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5206. Min Act: -0.1700
Data Index: 4327813 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5049. Min Act: -0.1700
Data Index: 2032141 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.4892. Min Act: -0.1700
Data Index: 6290318 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.4736. Min Act: -0.1700
Data Index: 5707059 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.4736. Min Act: -0.1700
Data Index: 1997562 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.4736. Min Act: -0.1700
Data Index: 6350914 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.4736. Min Act: -0.1700
Data Index: 3501428 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.4736. Min Act: -0.1700
Data Index: 4456502 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19