Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.4248. Min Act: -0.1700
Data Index: 721955 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.4573. Min Act: -0.1700
Data Index: 2431012 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.4248. Min Act: -0.1700
Data Index: 5662817 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.4248. Min Act: -0.1700
Data Index: 2572270 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.4410. Min Act: -0.1700
Data Index: 4695790 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.4410. Min Act: -0.1700
Data Index: 116322 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3921. Min Act: -0.1700
Data Index: 5737404 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3594. Min Act: -0.1700
Data Index: 1463627 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3594. Min Act: -0.1700
Data Index: 4602898 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3758. Min Act: -0.1700
Data Index: 2024997 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3758. Min Act: -0.1700
Data Index: 2271208 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3758. Min Act: -0.1700
Data Index: 3168071 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3594. Min Act: -0.1700
Data Index: 7476333 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3431. Min Act: -0.1700
Data Index: 500415 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3594. Min Act: -0.1700
Data Index: 1347550 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3594. Min Act: -0.1700
Data Index: 6470300 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.2938. Min Act: -0.1700
Data Index: 1021277 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3431. Min Act: -0.1700
Data Index: 1338011 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3431. Min Act: -0.1700
Data Index: 5493635 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4573. Min Range: -2.4573
Max Act: 2.3267. Min Act: -0.1700
Data Index: 7577872 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19