Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5095 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.9730. Min Act: -0.1700
Data Index: 8085062 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.8480. Min Act: -0.1700
Data Index: 7035718 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.8168. Min Act: -0.1700
Data Index: 99317 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.8168. Min Act: -0.1700
Data Index: 3573377 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.7855. Min Act: -0.1700
Data Index: 2406062 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.7855. Min Act: -0.1700
Data Index: 949577 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.7855. Min Act: -0.1700
Data Index: 5425720 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.7855. Min Act: -0.1700
Data Index: 6308764 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.7543. Min Act: -0.1700
Data Index: 2284626 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.7543. Min Act: -0.1700
Data Index: 1789288 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.7543. Min Act: -0.1700
Data Index: 3357526 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.7230. Min Act: -0.1700
Data Index: 8020162 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.7230. Min Act: -0.1700
Data Index: 4717488 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.6918. Min Act: -0.1700
Data Index: 7210237 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.6605. Min Act: -0.1700
Data Index: 4123604 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.6918. Min Act: -0.1700
Data Index: 1158254 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.6293. Min Act: -0.1700
Data Index: 6718318 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.6605. Min Act: -0.1700
Data Index: 3417823 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.6605. Min Act: -0.1700
Data Index: 3813209 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9730. Min Range: -5.9730
Max Act: 5.6605. Min Act: -0.1700
Data Index: 3626435 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19