Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 967 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3297. Min Range: -7.3297
Max Act: 7.3297. Min Act: -0.1700
Data Index: 8661045 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3297. Min Range: -7.3297
Max Act: 7.0797. Min Act: -0.1700
Data Index: 5190542 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3297. Min Range: -7.3297
Max Act: 7.0797. Min Act: -0.1700
Data Index: 3940474 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3297. Min Range: -7.3297
Max Act: 7.0172. Min Act: -0.1700
Data Index: 995922 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.9547. Min Act: -0.1700
Data Index: 6190766 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.9860. Min Act: -0.1700
Data Index: 5618029 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.9547. Min Act: -0.1700
Data Index: 8455425 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.9547. Min Act: -0.1700
Data Index: 966325 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.9547. Min Act: -0.1700
Data Index: 4774734 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.9235. Min Act: -0.1700
Data Index: 744365 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.9235. Min Act: -0.1700
Data Index: 3400929 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.9235. Min Act: -0.1700
Data Index: 2919528 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.8922. Min Act: -0.1700
Data Index: 6340443 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.9235. Min Act: -0.1700
Data Index: 6120152 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.8297. Min Act: -0.1700
Data Index: 1326638 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.8922. Min Act: -0.1700
Data Index: 8242684 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.8297. Min Act: -0.1700
Data Index: 3488371 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.8297. Min Act: -0.1700
Data Index: 2671759 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.8297. Min Act: -0.1700
Data Index: 5832360 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3297. Min Range: -7.3297
Max Act: 6.8297. Min Act: -0.1700
Data Index: 460735 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19