Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 339 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.4398. Min Act: -0.1700
Data Index: 8407876 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.4072. Min Act: -0.1700
Data Index: 7976743 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.4072. Min Act: -0.1700
Data Index: 1254056 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.3909. Min Act: -0.1700
Data Index: 3638071 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.3909. Min Act: -0.1700
Data Index: 6539856 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.3909. Min Act: -0.1700
Data Index: 1452071 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.3745. Min Act: -0.1700
Data Index: 4593102 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.3582. Min Act: -0.1700
Data Index: 7672544 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.3254. Min Act: -0.1700
Data Index: 6828669 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.3090. Min Act: -0.1700
Data Index: 2180252 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.3090. Min Act: -0.1700
Data Index: 8453952 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.3090. Min Act: -0.1700
Data Index: 307871 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.3090. Min Act: -0.1700
Data Index: 1889927 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.2925. Min Act: -0.1700
Data Index: 5484832 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.2925. Min Act: -0.1700
Data Index: 1732232 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.2925. Min Act: -0.1700
Data Index: 7672541 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.2925. Min Act: -0.1700
Data Index: 4729755 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.2925. Min Act: -0.1700
Data Index: 4612364 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.2925. Min Act: -0.1700
Data Index: 8158883 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4398. Min Range: -2.4398
Max Act: 2.2265. Min Act: -0.1700
Data Index: 4498440 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19