Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2515 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.3657. Min Range: -11.3657
Max Act: 11.3657. Min Act: -0.1700
Data Index: 7221167 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3657. Min Range: -11.3657
Max Act: 10.4282. Min Act: -0.1700
Data Index: 5364505 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3657. Min Range: -11.3657
Max Act: 10.2407. Min Act: -0.1700
Data Index: 148401 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3657. Min Range: -11.3657
Max Act: 10.0532. Min Act: -0.1698
Data Index: 4400582 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3657. Min Range: -11.3657
Max Act: 10.0532. Min Act: -0.1700
Data Index: 2414939 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.9282. Min Act: -0.1700
Data Index: 6607060 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.8657. Min Act: -0.1700
Data Index: 2077353 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.8032. Min Act: -0.1700
Data Index: 7463099 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.7407. Min Act: -0.1700
Data Index: 3226831 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.6782. Min Act: -0.1700
Data Index: 4077683 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.6157. Min Act: -0.1700
Data Index: 562000 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.6157. Min Act: -0.1700
Data Index: 6968580 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.6157. Min Act: -0.1700
Data Index: 6381947 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.6157. Min Act: -0.1700
Data Index: 2251828 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.5532. Min Act: -0.1700
Data Index: 6705362 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.5532. Min Act: -0.1700
Data Index: 8514856 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.4907. Min Act: -0.1700
Data Index: 5632114 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.4907. Min Act: -0.1700
Data Index: 3077636 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.4282. Min Act: -0.1700
Data Index: 5604865 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3657. Min Range: -11.3657
Max Act: 9.4907. Min Act: -0.1700
Data Index: 2915775 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19