Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4572 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2629. Min Range: -6.2629
Max Act: 6.2629. Min Act: -0.1700
Data Index: 4228323 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.9504. Min Act: -0.1700
Data Index: 6244174 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.9504. Min Act: -0.1700
Data Index: 3623961 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.8879. Min Act: -0.1700
Data Index: 7804217 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.9504. Min Act: -0.1700
Data Index: 6709886 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.8879. Min Act: -0.1700
Data Index: 228704 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.8879. Min Act: -0.1700
Data Index: 5457741 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.8879. Min Act: -0.1700
Data Index: 4869327 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.9191. Min Act: -0.1700
Data Index: 1529561 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.8879. Min Act: -0.1700
Data Index: 7035619 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.8879. Min Act: -0.1700
Data Index: 3490336 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.8566. Min Act: -0.1700
Data Index: 4683694 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.8566. Min Act: -0.1700
Data Index: 1060588 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.7941. Min Act: -0.1700
Data Index: 2393341 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.8254. Min Act: -0.1700
Data Index: 7398094 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.7629. Min Act: -0.1700
Data Index: 6391031 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.7941. Min Act: -0.1700
Data Index: 8710457 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.7004. Min Act: -0.1700
Data Index: 5879823 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.7316. Min Act: -0.1700
Data Index: 4463672 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2629. Min Range: -6.2629
Max Act: 5.7316. Min Act: -0.1700
Data Index: 3764054 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19