Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.9099. Min Act: -0.1700
Data Index: 1222466 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.7537. Min Act: -0.1700
Data Index: 5091594 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.6599. Min Act: -0.1700
Data Index: 3930334 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.6912. Min Act: -0.1700
Data Index: 2297725 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.6912. Min Act: -0.1700
Data Index: 4937216 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.6287. Min Act: -0.1700
Data Index: 8513314 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.6287. Min Act: -0.1700
Data Index: 1262399 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.5974. Min Act: -0.1700
Data Index: 8256192 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.5974. Min Act: -0.1700
Data Index: 2445490 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.5662. Min Act: -0.1700
Data Index: 85220 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.5349. Min Act: -0.1700
Data Index: 1033019 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.5037. Min Act: -0.1700
Data Index: 4659054 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.5349. Min Act: -0.1700
Data Index: 6044961 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.5037. Min Act: -0.1700
Data Index: 6668831 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.5037. Min Act: -0.1700
Data Index: 1151768 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.5037. Min Act: -0.1700
Data Index: 4466459 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.4724. Min Act: -0.1700
Data Index: 4902665 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.4412. Min Act: -0.1700
Data Index: 4750754 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.4724. Min Act: -0.1700
Data Index: 4606161 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9099. Min Range: -4.9099
Max Act: 4.4724. Min Act: -0.1700
Data Index: 412191 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19