Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4144 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.8029. Min Act: -0.1700
Data Index: 6989602 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.6779. Min Act: -0.1700
Data Index: 8698112 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.6154. Min Act: -0.1700
Data Index: 2706158 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.5841. Min Act: -0.1700
Data Index: 5916606 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.5216. Min Act: -0.1700
Data Index: 8059336 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.4591. Min Act: -0.1700
Data Index: 6048275 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.4904. Min Act: -0.1700
Data Index: 385815 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.4591. Min Act: -0.1700
Data Index: 6664986 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.4591. Min Act: -0.1700
Data Index: 6176424 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.4591. Min Act: -0.1700
Data Index: 3322574 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.3966. Min Act: -0.1700
Data Index: 1391486 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.4279. Min Act: -0.1700
Data Index: 4598692 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.3966. Min Act: -0.1700
Data Index: 532987 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.3966. Min Act: -0.1700
Data Index: 4955644 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.3341. Min Act: -0.1700
Data Index: 3857865 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.3341. Min Act: -0.1700
Data Index: 3242342 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.3341. Min Act: -0.1700
Data Index: 4593569 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.3654. Min Act: -0.1700
Data Index: 4800943 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.3029. Min Act: -0.1700
Data Index: 1091782 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8029. Min Range: -5.8029
Max Act: 5.3029. Min Act: -0.1700
Data Index: 4759979 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19