Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4755 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5169. Min Range: -5.5169
Max Act: 5.5169. Min Act: -0.1700
Data Index: 240822 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5169. Min Range: -5.5169
Max Act: 5.3919. Min Act: -0.1700
Data Index: 2129962 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5169. Min Range: -5.5169
Max Act: 5.3294. Min Act: -0.1700
Data Index: 3444903 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5169. Min Range: -5.5169
Max Act: 5.2356. Min Act: -0.1700
Data Index: 1217205 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5169. Min Range: -5.5169
Max Act: 5.1419. Min Act: -0.1700
Data Index: 4347888 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5169. Min Range: -5.5169
Max Act: 5.1106. Min Act: -0.1700
Data Index: 8440786 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5169. Min Range: -5.5169
Max Act: 5.0481. Min Act: -0.1700
Data Index: 8012301 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5169. Min Range: -5.5169
Max Act: 5.0481. Min Act: -0.1700
Data Index: 1482003 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.9544. Min Act: -0.1700
Data Index: 5730288 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.9856. Min Act: -0.1700
Data Index: 7566645 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.9544. Min Act: -0.1700
Data Index: 3867705 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.9544. Min Act: -0.1700
Data Index: 8678396 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.8919. Min Act: -0.1700
Data Index: 177321 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.8606. Min Act: -0.1700
Data Index: 1877837 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.8919. Min Act: -0.1700
Data Index: 2324619 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.9231. Min Act: -0.1700
Data Index: 8232211 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.8294. Min Act: -0.1700
Data Index: 883501 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.7981. Min Act: -0.1700
Data Index: 6915936 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.7669. Min Act: -0.1700
Data Index: 2887316 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5169. Min Range: -5.5169
Max Act: 4.7669. Min Act: -0.1700
Data Index: 3874193 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19