Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4453 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.9771. Min Act: -0.1700
Data Index: 2554057 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.6959. Min Act: -0.1700
Data Index: 850842 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.5084. Min Act: -0.1700
Data Index: 4804969 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.4771. Min Act: -0.1700
Data Index: 6932159 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.4459. Min Act: -0.1700
Data Index: 8606810 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.3834. Min Act: -0.1700
Data Index: 1836715 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.3834. Min Act: -0.1700
Data Index: 2125227 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.3834. Min Act: -0.1700
Data Index: 2244545 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.3834. Min Act: -0.1700
Data Index: 4065228 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.3521. Min Act: -0.1700
Data Index: 4256249 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.2584. Min Act: -0.1700
Data Index: 7103421 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.2896. Min Act: -0.1700
Data Index: 3404446 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.2896. Min Act: -0.1700
Data Index: 591822 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.2896. Min Act: -0.1700
Data Index: 659018 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.3209. Min Act: -0.1700
Data Index: 5171715 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.2584. Min Act: -0.1700
Data Index: 248154 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.2271. Min Act: -0.1700
Data Index: 8406513 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.1959. Min Act: -0.1700
Data Index: 3007491 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.1959. Min Act: -0.1700
Data Index: 8662555 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9771. Min Range: -6.9771
Max Act: 6.1959. Min Act: -0.1700
Data Index: 6152441 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19