Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5204 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.6396. Min Act: -0.1700
Data Index: 247133 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.3584. Min Act: -0.1700
Data Index: 2115901 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.2959. Min Act: -0.1700
Data Index: 2441306 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.2646. Min Act: -0.1700
Data Index: 4154846 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.2646. Min Act: -0.1700
Data Index: 3804136 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.2646. Min Act: -0.1700
Data Index: 8222883 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.2646. Min Act: -0.1700
Data Index: 4154847 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.2021. Min Act: -0.1700
Data Index: 4479984 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.2021. Min Act: -0.1700
Data Index: 3298442 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.1396. Min Act: -0.1700
Data Index: 987691 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.1396. Min Act: -0.1700
Data Index: 6668488 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.1396. Min Act: -0.1700
Data Index: 3804134 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.1396. Min Act: -0.1700
Data Index: 6994822 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.1084. Min Act: -0.1700
Data Index: 4643985 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.1084. Min Act: -0.1700
Data Index: 1391427 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.1084. Min Act: -0.1700
Data Index: 6731360 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.1084. Min Act: -0.1700
Data Index: 7497220 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.0771. Min Act: -0.1700
Data Index: 6592902 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.0771. Min Act: -0.1700
Data Index: 5748881 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.0771. Min Act: -0.1700
Data Index: 6754503 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19