Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2837 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2349. Min Range: -4.2349
Max Act: 4.2349. Min Act: -0.1700
Data Index: 884054 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2349. Min Range: -4.2349
Max Act: 4.1724. Min Act: -0.1700
Data Index: 8106006 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2349. Min Range: -4.2349
Max Act: 4.0786. Min Act: -0.1700
Data Index: 884053 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2349. Min Range: -4.2349
Max Act: 4.0786. Min Act: -0.1700
Data Index: 102699 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2349. Min Range: -4.2349
Max Act: 4.0473. Min Act: -0.1700
Data Index: 5500630 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2349. Min Range: -4.2349
Max Act: 4.0473. Min Act: -0.1700
Data Index: 530310 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2349. Min Range: -4.2349
Max Act: 4.0473. Min Act: -0.1700
Data Index: 2384558 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2349. Min Range: -4.2349
Max Act: 4.0161. Min Act: -0.1700
Data Index: 4510780 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.9848. Min Act: -0.1700
Data Index: 2017855 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.9848. Min Act: -0.1700
Data Index: 4382773 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.9848. Min Act: -0.1700
Data Index: 6012745 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.9536. Min Act: -0.1700
Data Index: 5397980 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.9223. Min Act: -0.1700
Data Index: 3820980 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.9223. Min Act: -0.1700
Data Index: 6139751 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.9223. Min Act: -0.1700
Data Index: 8455503 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.9223. Min Act: -0.1700
Data Index: 3959355 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.8910. Min Act: -0.1700
Data Index: 3818262 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.9223. Min Act: -0.1700
Data Index: 8400025 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.9223. Min Act: -0.1700
Data Index: 87566 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2349. Min Range: -4.2349
Max Act: 3.8910. Min Act: -0.1700
Data Index: 6552090 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19