Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 946 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4436. Min Range: -8.4436
Max Act: 8.4436. Min Act: -0.1700
Data Index: 4062934 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4436. Min Range: -8.4436
Max Act: 8.4436. Min Act: -0.1700
Data Index: 2936926 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4436. Min Range: -8.4436
Max Act: 8.2561. Min Act: -0.1700
Data Index: 1789554 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4436. Min Range: -8.4436
Max Act: 8.1311. Min Act: -0.1700
Data Index: 1101778 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4436. Min Range: -8.4436
Max Act: 8.1936. Min Act: -0.1700
Data Index: 4361131 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4436. Min Range: -8.4436
Max Act: 8.1311. Min Act: -0.1700
Data Index: 5078239 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4436. Min Range: -8.4436
Max Act: 8.0374. Min Act: -0.1700
Data Index: 7860591 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4436. Min Range: -8.4436
Max Act: 8.0686. Min Act: -0.1700
Data Index: 1981111 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4436. Min Range: -8.4436
Max Act: 7.9749. Min Act: -0.1700
Data Index: 3243906 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4436. Min Range: -8.4436
Max Act: 8.0374. Min Act: -0.1700
Data Index: 7427767 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4436. Min Range: -8.4436
Max Act: 7.9436. Min Act: -0.1700
Data Index: 3582891 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4436. Min Range: -8.4436
Max Act: 7.8811. Min Act: -0.1700
Data Index: 6548750 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4436. Min Range: -8.4436
Max Act: 7.8811. Min Act: -0.1700
Data Index: 5281506 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4436. Min Range: -8.4436
Max Act: 7.8811. Min Act: -0.1700
Data Index: 4485254 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4436. Min Range: -8.4436
Max Act: 7.9436. Min Act: -0.1700
Data Index: 6039831 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4436. Min Range: -8.4436
Max Act: 7.8499. Min Act: -0.1700
Data Index: 8052013 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4436. Min Range: -8.4436
Max Act: 7.7249. Min Act: -0.1700
Data Index: 2807030 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4436. Min Range: -8.4436
Max Act: 7.8811. Min Act: -0.1700
Data Index: 178982 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4436. Min Range: -8.4436
Max Act: 7.8811. Min Act: -0.1700
Data Index: 4320443 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4436. Min Range: -8.4436
Max Act: 7.7874. Min Act: -0.1700
Data Index: 5976295 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19