Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 767 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.7040. Min Act: -0.1700
Data Index: 5730537 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.5165. Min Act: -0.1700
Data Index: 3419392 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.4853. Min Act: -0.1700
Data Index: 887288 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.4853. Min Act: -0.1700
Data Index: 319239 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.4540. Min Act: -0.1700
Data Index: 4616252 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.4540. Min Act: -0.1700
Data Index: 2432852 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.4540. Min Act: -0.1700
Data Index: 8450640 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.4228. Min Act: -0.1700
Data Index: 826380 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.4540. Min Act: -0.1700
Data Index: 6773418 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.4228. Min Act: -0.1700
Data Index: 3895068 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.4228. Min Act: -0.1700
Data Index: 1389026 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.3603. Min Act: -0.1700
Data Index: 3642848 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.3915. Min Act: -0.1700
Data Index: 5883621 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.3603. Min Act: -0.1700
Data Index: 5010768 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.3915. Min Act: -0.1700
Data Index: 963761 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.3603. Min Act: -0.1700
Data Index: 6108999 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.3603. Min Act: -0.1700
Data Index: 2575355 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.3603. Min Act: -0.1700
Data Index: 4437338 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.3290. Min Act: -0.1700
Data Index: 5259375 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7040. Min Range: -5.7040
Max Act: 5.3290. Min Act: -0.1700
Data Index: 5259378 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19