Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2407. Min Range: -7.2407
Max Act: 7.2407. Min Act: -0.1700
Data Index: 4060825 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2407. Min Range: -7.2407
Max Act: 7.0532. Min Act: -0.1700
Data Index: 997101 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2407. Min Range: -7.2407
Max Act: 7.0220. Min Act: -0.1700
Data Index: 5540834 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.9595. Min Act: -0.1700
Data Index: 3376080 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.7407. Min Act: -0.1700
Data Index: 4753920 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.6782. Min Act: -0.1700
Data Index: 954971 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.6157. Min Act: -0.1700
Data Index: 7601516 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.6470. Min Act: -0.1700
Data Index: 2160288 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.6157. Min Act: -0.1700
Data Index: 8755861 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.5845. Min Act: -0.1700
Data Index: 2887876 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.5845. Min Act: -0.1700
Data Index: 2423740 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.5532. Min Act: -0.1700
Data Index: 532627 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.5532. Min Act: -0.1700
Data Index: 7559252 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.5532. Min Act: -0.1700
Data Index: 1912817 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.4907. Min Act: -0.1700
Data Index: 1913395 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.5220. Min Act: -0.1700
Data Index: 1004853 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.4282. Min Act: -0.1700
Data Index: 6880857 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.4595. Min Act: -0.1700
Data Index: 8289148 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.4595. Min Act: -0.1700
Data Index: 5837712 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2407. Min Range: -7.2407
Max Act: 6.4282. Min Act: -0.1700
Data Index: 5389650 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19