Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5643 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.9002. Min Act: -0.1700
Data Index: 3927484 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.8048. Min Act: -0.1700
Data Index: 403689 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.7889. Min Act: -0.1700
Data Index: 8086178 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.7411. Min Act: -0.1700
Data Index: 4740210 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.7730. Min Act: -0.1700
Data Index: 3954763 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.7251. Min Act: -0.1700
Data Index: 2277778 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.7251. Min Act: -0.1700
Data Index: 3881724 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.7251. Min Act: -0.1700
Data Index: 2004610 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.7091. Min Act: -0.1700
Data Index: 1479481 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.7251. Min Act: -0.1700
Data Index: 429832 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.6931. Min Act: -0.1700
Data Index: 6387276 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.6611. Min Act: -0.1700
Data Index: 1437233 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.6611. Min Act: -0.1700
Data Index: 967725 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.6611. Min Act: -0.1700
Data Index: 951607 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.6450. Min Act: -0.1700
Data Index: 6859656 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.6611. Min Act: -0.1700
Data Index: 3585089 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.6611. Min Act: -0.1700
Data Index: 2055392 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.6611. Min Act: -0.1700
Data Index: 5500228 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.6450. Min Act: -0.1700
Data Index: 1383379 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9002. Min Range: -2.9002
Max Act: 2.6450. Min Act: -0.1700
Data Index: 4547594 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19