Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1810 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.8099. Min Act: -0.1700
Data Index: 2294023 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.7162. Min Act: -0.1700
Data Index: 8293712 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.6537. Min Act: -0.1700
Data Index: 2408199 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.6224. Min Act: -0.1700
Data Index: 8751782 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.5599. Min Act: -0.1700
Data Index: 6873168 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.5599. Min Act: -0.1700
Data Index: 3014837 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4974. Min Act: -0.1700
Data Index: 2357889 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4662. Min Act: -0.1700
Data Index: 437628 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4662. Min Act: -0.1700
Data Index: 1011965 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4349. Min Act: -0.1700
Data Index: 4175956 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4037. Min Act: -0.1700
Data Index: 7338230 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 8261965 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4037. Min Act: -0.1700
Data Index: 6515375 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 2805765 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 842266 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 7500992 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 7467378 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 3775457 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 4519374 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 1295146 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19