Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2747 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3019. Min Range: -8.3019
Max Act: 8.3019. Min Act: -0.1700
Data Index: 8545213 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3019. Min Range: -8.3019
Max Act: 8.1769. Min Act: -0.1700
Data Index: 416661 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3019. Min Range: -8.3019
Max Act: 8.1769. Min Act: -0.1700
Data Index: 1621492 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3019. Min Range: -8.3019
Max Act: 8.1144. Min Act: -0.1700
Data Index: 198589 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.9894. Min Act: -0.1700
Data Index: 4162379 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.9894. Min Act: -0.1700
Data Index: 2396395 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.9269. Min Act: -0.1700
Data Index: 8008798 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.9269. Min Act: -0.1700
Data Index: 3272466 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.9269. Min Act: -0.1700
Data Index: 5061524 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.9269. Min Act: -0.1700
Data Index: 7188889 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.8644. Min Act: -0.1700
Data Index: 4318106 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.8019. Min Act: -0.1700
Data Index: 630189 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.8019. Min Act: -0.1700
Data Index: 3728944 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.8019. Min Act: -0.1700
Data Index: 198590 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.7394. Min Act: -0.1700
Data Index: 4215175 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.7394. Min Act: -0.1700
Data Index: 7173197 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.7394. Min Act: -0.1700
Data Index: 4309965 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.7394. Min Act: -0.1700
Data Index: 7427309 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.7394. Min Act: -0.1700
Data Index: 8784035 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3019. Min Range: -8.3019
Max Act: 7.8019. Min Act: -0.1700
Data Index: 7042658 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19