Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1695 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.8044. Min Act: -0.1700
Data Index: 4707073 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.7106. Min Act: -0.1699
Data Index: 2721945 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.6324. Min Act: -0.1700
Data Index: 5943598 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.5854. Min Act: -0.1700
Data Index: 7731317 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.5698. Min Act: -0.1700
Data Index: 1313193 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.5541. Min Act: -0.1700
Data Index: 8559915 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.5228. Min Act: -0.1700
Data Index: 3543944 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.4915. Min Act: -0.1700
Data Index: 3455262 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.4758. Min Act: -0.1699
Data Index: 3239848 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.4758. Min Act: -0.1700
Data Index: 1673056 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.4601. Min Act: -0.1700
Data Index: 8378025 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.4445. Min Act: -0.1700
Data Index: 8173703 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.4288. Min Act: -0.1700
Data Index: 3488372 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.4288. Min Act: -0.1700
Data Index: 8639664 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.4445. Min Act: -0.1700
Data Index: 4657496 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.4288. Min Act: -0.1700
Data Index: 2569205 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.4131. Min Act: -0.1691
Data Index: 5735992 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.4131. Min Act: -0.1700
Data Index: 8002438 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.3974. Min Act: -0.1700
Data Index: 7821084 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8044. Min Range: -3.8044
Max Act: 3.3818. Min Act: -0.1663
Data Index: 5226014 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19