Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 647 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.8703. Min Act: -0.1700
Data Index: 273327 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.8703. Min Act: -0.1700
Data Index: 8051448 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.8078. Min Act: -0.1700
Data Index: 4214168 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.7766. Min Act: -0.1700
Data Index: 2456165 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.7453. Min Act: -0.1700
Data Index: 8130322 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.7453. Min Act: -0.1700
Data Index: 4620071 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.7141. Min Act: -0.1700
Data Index: 2521456 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.6516. Min Act: -0.1700
Data Index: 4514528 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.6516. Min Act: -0.1700
Data Index: 5875564 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.6516. Min Act: -0.1700
Data Index: 5636889 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.6203. Min Act: -0.1700
Data Index: 5120024 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.6203. Min Act: -0.1700
Data Index: 433513 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.5578. Min Act: -0.1700
Data Index: 296539 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.5578. Min Act: -0.1700
Data Index: 6489801 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.5578. Min Act: -0.1700
Data Index: 527832 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.5578. Min Act: -0.1700
Data Index: 3606386 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.5578. Min Act: -0.1700
Data Index: 2661644 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.4953. Min Act: -0.1700
Data Index: 4027478 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.5266. Min Act: -0.1700
Data Index: 3912599 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8703. Min Range: -5.8703
Max Act: 5.5266. Min Act: -0.1700
Data Index: 2242058 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19