Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1971 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.9645. Min Act: -0.1700
Data Index: 761300 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.9020. Min Act: -0.1700
Data Index: 3639060 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.8707. Min Act: -0.1700
Data Index: 8421031 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.8082. Min Act: -0.1700
Data Index: 1087731 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.7770. Min Act: -0.1700
Data Index: 4822423 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.7770. Min Act: -0.1700
Data Index: 2427844 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.7457. Min Act: -0.1700
Data Index: 7397622 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.7145. Min Act: -0.1700
Data Index: 3995080 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.6832. Min Act: -0.1700
Data Index: 5168687 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.6207. Min Act: -0.1700
Data Index: 2505117 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.5895. Min Act: -0.1700
Data Index: 2505106 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.5582. Min Act: -0.1700
Data Index: 8638039 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.5582. Min Act: -0.1700
Data Index: 2505112 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.5270. Min Act: -0.1700
Data Index: 2505105 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.5270. Min Act: -0.1700
Data Index: 7983612 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.5270. Min Act: -0.1700
Data Index: 6958615 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.5270. Min Act: -0.1700
Data Index: 1994208 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.4957. Min Act: -0.1700
Data Index: 5517572 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.4957. Min Act: -0.1700
Data Index: 2411329 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.4645. Min Act: -0.1700
Data Index: 6787244 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19