Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2629 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0127. Min Range: -3.0127
Max Act: 3.0127. Min Act: -0.1700
Data Index: 7592593 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.9811. Min Act: -0.1700
Data Index: 1920937 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0127. Min Range: -3.0127
Max Act: 3.0127. Min Act: -0.1700
Data Index: 6286529 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.9336. Min Act: -0.1700
Data Index: 3934286 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.9019. Min Act: -0.1700
Data Index: 142073 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.8861. Min Act: -0.1700
Data Index: 910409 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.8543. Min Act: -0.1700
Data Index: 2705341 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.8543. Min Act: -0.1700
Data Index: 3303087 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.8543. Min Act: -0.1700
Data Index: 3055449 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.8225. Min Act: -0.1700
Data Index: 8253443 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.8225. Min Act: -0.1700
Data Index: 2020219 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.8225. Min Act: -0.1700
Data Index: 8200025 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.8225. Min Act: -0.1700
Data Index: 3005514 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.8066. Min Act: -0.1700
Data Index: 326529 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.7907. Min Act: -0.1700
Data Index: 1670381 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.7907. Min Act: -0.1700
Data Index: 4509232 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.7907. Min Act: -0.1700
Data Index: 4019412 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.7747. Min Act: -0.1700
Data Index: 6202718 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.7747. Min Act: -0.1700
Data Index: 7406829 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0127. Min Range: -3.0127
Max Act: 2.7747. Min Act: -0.1700
Data Index: 2725590 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19