Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1061 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.7678. Min Act: -0.1700
Data Index: 3730257 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.6427. Min Act: -0.1700
Data Index: 4848942 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.5175. Min Act: -0.1700
Data Index: 5735809 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.4861. Min Act: -0.1700
Data Index: 544604 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.4548. Min Act: -0.1700
Data Index: 6681926 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3921. Min Act: -0.1700
Data Index: 6591351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3450. Min Act: -0.1700
Data Index: 4060379 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3921. Min Act: -0.1700
Data Index: 5288366 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3764. Min Act: -0.1700
Data Index: 2178339 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3450. Min Act: -0.1700
Data Index: 8070555 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3450. Min Act: -0.1700
Data Index: 2775316 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3450. Min Act: -0.1700
Data Index: 2326403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3450. Min Act: -0.1700
Data Index: 8050950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3450. Min Act: -0.1700
Data Index: 4956719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3450. Min Act: -0.1700
Data Index: 7488932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3450. Min Act: -0.1700
Data Index: 1981609 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3450. Min Act: -0.1700
Data Index: 5733248 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3450. Min Act: -0.1700
Data Index: 8193714 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3764. Min Act: -0.1700
Data Index: 7122252 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7678. Min Range: -3.7678
Max Act: 3.3450. Min Act: -0.1700
Data Index: 4936638 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19