Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3989 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.6939. Min Act: -0.1700
Data Index: 3499151 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.7251. Min Act: -0.1700
Data Index: 1297698 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.5689. Min Act: -0.1700
Data Index: 2885325 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.5689. Min Act: -0.1700
Data Index: 3010273 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.5689. Min Act: -0.1700
Data Index: 7147407 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.5376. Min Act: -0.1700
Data Index: 8080486 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.4439. Min Act: -0.1700
Data Index: 1215581 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.4439. Min Act: -0.1700
Data Index: 318437 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.4126. Min Act: -0.1700
Data Index: 619465 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.4126. Min Act: -0.1700
Data Index: 1068209 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3814. Min Act: -0.1700
Data Index: 2703759 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3814. Min Act: -0.1700
Data Index: 4188919 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3189. Min Act: -0.1700
Data Index: 3691840 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3189. Min Act: -0.1700
Data Index: 4581245 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3501. Min Act: -0.1700
Data Index: 1342662 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3189. Min Act: -0.1700
Data Index: 2435665 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.2876. Min Act: -0.1700
Data Index: 5134580 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.2564. Min Act: -0.1700
Data Index: 5464816 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.2876. Min Act: -0.1700
Data Index: 8114706 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.2564. Min Act: -0.1700
Data Index: 5652361 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19