Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2726 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7787. Min Range: -7.7787
Max Act: 7.7787. Min Act: -0.1700
Data Index: 8600740 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7787. Min Range: -7.7787
Max Act: 7.3724. Min Act: -0.1700
Data Index: 7596397 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7787. Min Range: -7.7787
Max Act: 7.3099. Min Act: -0.1700
Data Index: 6469678 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7787. Min Range: -7.7787
Max Act: 7.2474. Min Act: -0.1700
Data Index: 7294645 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7787. Min Range: -7.7787
Max Act: 7.2162. Min Act: -0.1700
Data Index: 1689358 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7787. Min Range: -7.7787
Max Act: 7.2162. Min Act: -0.1700
Data Index: 2952772 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7787. Min Range: -7.7787
Max Act: 7.1537. Min Act: -0.1700
Data Index: 7992179 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7787. Min Range: -7.7787
Max Act: 7.1849. Min Act: -0.1700
Data Index: 8520960 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7787. Min Range: -7.7787
Max Act: 7.1537. Min Act: -0.1700
Data Index: 1156226 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7787. Min Range: -7.7787
Max Act: 7.1224. Min Act: -0.1700
Data Index: 2952774 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7787. Min Range: -7.7787
Max Act: 6.9974. Min Act: -0.1700
Data Index: 4881309 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7787. Min Range: -7.7787
Max Act: 6.9974. Min Act: -0.1700
Data Index: 3682752 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7787. Min Range: -7.7787
Max Act: 6.9974. Min Act: -0.1700
Data Index: 1639807 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7787. Min Range: -7.7787
Max Act: 6.9662. Min Act: -0.1700
Data Index: 817469 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7787. Min Range: -7.7787
Max Act: 6.8724. Min Act: -0.1700
Data Index: 6110419 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7787. Min Range: -7.7787
Max Act: 6.9037. Min Act: -0.1700
Data Index: 8705287 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7787. Min Range: -7.7787
Max Act: 6.8724. Min Act: -0.1700
Data Index: 4826513 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7787. Min Range: -7.7787
Max Act: 6.9037. Min Act: -0.1700
Data Index: 8786705 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7787. Min Range: -7.7787
Max Act: 6.8724. Min Act: -0.1700
Data Index: 7928366 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7787. Min Range: -7.7787
Max Act: 6.8412. Min Act: -0.1700
Data Index: 2446180 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19