Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.9388. Min Act: -0.1700
Data Index: 1190855 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.6263. Min Act: -0.1700
Data Index: 954563 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.5638. Min Act: -0.1700
Data Index: 3285783 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.5326. Min Act: -0.1700
Data Index: 2485857 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.4388. Min Act: -0.1700
Data Index: 7849249 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.4388. Min Act: -0.1700
Data Index: 2567423 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3763. Min Act: -0.1700
Data Index: 5269093 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3763. Min Act: -0.1700
Data Index: 7102535 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3451. Min Act: -0.1700
Data Index: 8668902 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3451. Min Act: -0.1700
Data Index: 6355675 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3451. Min Act: -0.1700
Data Index: 4832362 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3138. Min Act: -0.1700
Data Index: 2081051 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2513. Min Act: -0.1700
Data Index: 8019572 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2513. Min Act: -0.1700
Data Index: 5098644 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2201. Min Act: -0.1700
Data Index: 7808633 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2513. Min Act: -0.1700
Data Index: 7487544 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2513. Min Act: -0.1700
Data Index: 6546266 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2513. Min Act: -0.1700
Data Index: 4327048 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2201. Min Act: -0.1700
Data Index: 2327888 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2201. Min Act: -0.1700
Data Index: 4509015 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19