Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0169. Min Range: -8.0169
Max Act: 8.0169. Min Act: -0.1700
Data Index: 2976686 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0169. Min Range: -8.0169
Max Act: 7.4232. Min Act: -0.1700
Data Index: 1979752 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0169. Min Range: -8.0169
Max Act: 7.3919. Min Act: -0.1700
Data Index: 8654221 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0169. Min Range: -8.0169
Max Act: 7.2044. Min Act: -0.1700
Data Index: 8271343 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0169. Min Range: -8.0169
Max Act: 7.2044. Min Act: -0.1700
Data Index: 1669374 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0169. Min Range: -8.0169
Max Act: 7.1732. Min Act: -0.1700
Data Index: 7296262 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0169. Min Range: -8.0169
Max Act: 7.1419. Min Act: -0.1700
Data Index: 7523737 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0169. Min Range: -8.0169
Max Act: 7.0482. Min Act: -0.1700
Data Index: 1483498 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0169. Min Range: -8.0169
Max Act: 7.0482. Min Act: -0.1700
Data Index: 8723418 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0169. Min Range: -8.0169
Max Act: 7.0169. Min Act: -0.1700
Data Index: 2165356 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0169. Min Range: -8.0169
Max Act: 7.0169. Min Act: -0.1700
Data Index: 5597114 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0169. Min Range: -8.0169
Max Act: 6.9857. Min Act: -0.1700
Data Index: 7649423 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0169. Min Range: -8.0169
Max Act: 6.9857. Min Act: -0.1700
Data Index: 4869191 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0169. Min Range: -8.0169
Max Act: 6.9544. Min Act: -0.1700
Data Index: 910728 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0169. Min Range: -8.0169
Max Act: 6.9857. Min Act: -0.1700
Data Index: 6384351 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0169. Min Range: -8.0169
Max Act: 6.9232. Min Act: -0.1700
Data Index: 4632506 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0169. Min Range: -8.0169
Max Act: 6.8919. Min Act: -0.1700
Data Index: 424317 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0169. Min Range: -8.0169
Max Act: 6.8919. Min Act: -0.1700
Data Index: 750337 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0169. Min Range: -8.0169
Max Act: 6.8607. Min Act: -0.1700
Data Index: 4326315 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0169. Min Range: -8.0169
Max Act: 6.8294. Min Act: -0.1700
Data Index: 8580426 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19