Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2427. Min Range: -6.2427
Max Act: 6.2427. Min Act: -0.1700
Data Index: 3608399 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2427. Min Range: -6.2427
Max Act: 6.2114. Min Act: -0.1700
Data Index: 3864845 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2427. Min Range: -6.2427
Max Act: 6.2114. Min Act: -0.1700
Data Index: 7542732 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.9614. Min Act: -0.1700
Data Index: 578314 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.9302. Min Act: -0.1700
Data Index: 3973906 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.8989. Min Act: -0.1700
Data Index: 2149638 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.8989. Min Act: -0.1700
Data Index: 7002326 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.8989. Min Act: -0.1700
Data Index: 7400836 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.8677. Min Act: -0.1700
Data Index: 5711532 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.8677. Min Act: -0.1700
Data Index: 3658158 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.8364. Min Act: -0.1700
Data Index: 4956040 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.8052. Min Act: -0.1700
Data Index: 3661414 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.8052. Min Act: -0.1700
Data Index: 1618049 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.7739. Min Act: -0.1700
Data Index: 4108007 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.7739. Min Act: -0.1700
Data Index: 4907554 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.7739. Min Act: -0.1700
Data Index: 4221462 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.7739. Min Act: -0.1700
Data Index: 41753 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.7427. Min Act: -0.1700
Data Index: 4292666 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.7427. Min Act: -0.1700
Data Index: 444438 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2427. Min Range: -6.2427
Max Act: 5.7427. Min Act: -0.1700
Data Index: 8143961 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19