Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.7008. Min Act: -0.1700
Data Index: 3273311 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.6070. Min Act: -0.1700
Data Index: 4487852 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.5445. Min Act: -0.1700
Data Index: 5273474 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.5445. Min Act: -0.1700
Data Index: 1199531 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.4820. Min Act: -0.1700
Data Index: 4488102 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.4820. Min Act: -0.1700
Data Index: 4793833 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.4508. Min Act: -0.1700
Data Index: 3291680 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.4195. Min Act: -0.1700
Data Index: 8733110 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.4195. Min Act: -0.1700
Data Index: 3088258 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.3883. Min Act: -0.1700
Data Index: 1987265 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.3883. Min Act: -0.1700
Data Index: 5194165 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.3883. Min Act: -0.1700
Data Index: 218085 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.3883. Min Act: -0.1700
Data Index: 7840112 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.3883. Min Act: -0.1700
Data Index: 6220921 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.3258. Min Act: -0.1700
Data Index: 6889257 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.2945. Min Act: -0.1700
Data Index: 7285432 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.2945. Min Act: -0.1700
Data Index: 1341815 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.2945. Min Act: -0.1700
Data Index: 406176 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.3258. Min Act: -0.1700
Data Index: 6847163 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7008. Min Range: -5.7008
Max Act: 5.2633. Min Act: -0.1700
Data Index: 4444412 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19