Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4308 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5880. Min Range: -9.5880
Max Act: 9.5880. Min Act: -0.1700
Data Index: 8733017 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5880. Min Range: -9.5880
Max Act: 9.5255. Min Act: -0.1700
Data Index: 6723164 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5880. Min Range: -9.5880
Max Act: 9.0880. Min Act: -0.1700
Data Index: 7585621 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5880. Min Range: -9.5880
Max Act: 9.1505. Min Act: -0.1700
Data Index: 2507903 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5880. Min Range: -9.5880
Max Act: 9.0880. Min Act: -0.1700
Data Index: 4334308 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5880. Min Range: -9.5880
Max Act: 9.0255. Min Act: -0.1700
Data Index: 5302009 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.9630. Min Act: -0.1700
Data Index: 917343 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.9005. Min Act: -0.1700
Data Index: 1516873 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.9005. Min Act: -0.1700
Data Index: 3056112 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.9005. Min Act: -0.1700
Data Index: 2286459 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.9005. Min Act: -0.1700
Data Index: 3112767 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.8380. Min Act: -0.1700
Data Index: 4169239 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.8380. Min Act: -0.1700
Data Index: 937329 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.8380. Min Act: -0.1700
Data Index: 5701308 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.7755. Min Act: -0.1700
Data Index: 1754624 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.7755. Min Act: -0.1700
Data Index: 107169 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.7130. Min Act: -0.1700
Data Index: 2083460 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.7755. Min Act: -0.1700
Data Index: 4425351 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.7130. Min Act: -0.1700
Data Index: 6309449 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5880. Min Range: -9.5880
Max Act: 8.7130. Min Act: -0.1700
Data Index: 2527561 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19