Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4251 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.6901. Min Act: -0.1700
Data Index: 3543009 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.5026. Min Act: -0.1700
Data Index: 3877333 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.5026. Min Act: -0.1700
Data Index: 3781358 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.5026. Min Act: -0.1700
Data Index: 6282136 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.4401. Min Act: -0.1700
Data Index: 7375573 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.4401. Min Act: -0.1700
Data Index: 7922596 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.3776. Min Act: -0.1700
Data Index: 2129686 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.3151. Min Act: -0.1700
Data Index: 4363494 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.3151. Min Act: -0.1700
Data Index: 1579931 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.2526. Min Act: -0.1700
Data Index: 593759 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.1901. Min Act: -0.1700
Data Index: 1306137 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.0651. Min Act: -0.1700
Data Index: 3211096 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.1276. Min Act: -0.1700
Data Index: 4004113 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.0651. Min Act: -0.1700
Data Index: 1434899 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.0651. Min Act: -0.1700
Data Index: 7518572 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.0651. Min Act: -0.1700
Data Index: 4160295 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.0651. Min Act: -0.1700
Data Index: 5668329 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6901. Min Range: -8.6901
Max Act: 7.9400. Min Act: -0.1700
Data Index: 2395185 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6901. Min Range: -8.6901
Max Act: 8.0026. Min Act: -0.1700
Data Index: 6663282 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6901. Min Range: -8.6901
Max Act: 7.9400. Min Act: -0.1700
Data Index: 5697566 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19