Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 960 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.4060. Min Act: -0.1700
Data Index: 7887059 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2810. Min Act: -0.1700
Data Index: 900933 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.3435. Min Act: -0.1700
Data Index: 2172331 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.3748. Min Act: -0.1700
Data Index: 7080210 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2810. Min Act: -0.1700
Data Index: 5382641 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2810. Min Act: -0.1700
Data Index: 1592916 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2498. Min Act: -0.1700
Data Index: 110619 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2498. Min Act: -0.1700
Data Index: 1335173 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2185. Min Act: -0.1700
Data Index: 8030575 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2498. Min Act: -0.1700
Data Index: 326627 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2498. Min Act: -0.1700
Data Index: 735818 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.1872. Min Act: -0.1700
Data Index: 5692415 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2185. Min Act: -0.1700
Data Index: 95919 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2498. Min Act: -0.1700
Data Index: 6170922 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2185. Min Act: -0.1700
Data Index: 3203433 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.2498. Min Act: -0.1700
Data Index: 3541752 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.1872. Min Act: -0.1700
Data Index: 1823381 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.1872. Min Act: -0.1700
Data Index: 7980795 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.1560. Min Act: -0.1700
Data Index: 452249 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4060. Min Range: -4.4060
Max Act: 4.1560. Min Act: -0.1700
Data Index: 5005597 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19