Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.8293. Min Act: -0.1700
Data Index: 3106289 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.7981. Min Act: -0.1700
Data Index: 3291506 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.6731. Min Act: -0.1700
Data Index: 826473 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.6106. Min Act: -0.1700
Data Index: 298451 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.5793. Min Act: -0.1700
Data Index: 8325064 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.5793. Min Act: -0.1700
Data Index: 2673581 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.5168. Min Act: -0.1700
Data Index: 1761463 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.5168. Min Act: -0.1700
Data Index: 4837153 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4856. Min Act: -0.1700
Data Index: 7165766 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4543. Min Act: -0.1700
Data Index: 7874676 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4543. Min Act: -0.1700
Data Index: 2750590 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4856. Min Act: -0.1700
Data Index: 6131665 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4543. Min Act: -0.1700
Data Index: 4682991 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4231. Min Act: -0.1700
Data Index: 7289088 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4231. Min Act: -0.1700
Data Index: 7464791 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4231. Min Act: -0.1700
Data Index: 5672383 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4231. Min Act: -0.1700
Data Index: 3649501 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4231. Min Act: -0.1700
Data Index: 2826891 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4231. Min Act: -0.1700
Data Index: 6498055 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8293. Min Range: -4.8293
Max Act: 4.4231. Min Act: -0.1700
Data Index: 1070212 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19