Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0719. Min Range: -2.0719
Max Act: 2.0719. Min Act: -0.1700
Data Index: 2401962 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0719. Min Range: -2.0719
Max Act: 2.0214. Min Act: -0.1700
Data Index: 6285407 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0719. Min Range: -2.0719
Max Act: 2.0382. Min Act: -0.1700
Data Index: 9032 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0719. Min Range: -2.0719
Max Act: 2.0214. Min Act: -0.1700
Data Index: 2046870 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0719. Min Range: -2.0719
Max Act: 2.0045. Min Act: -0.1700
Data Index: 7075763 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0719. Min Range: -2.0719
Max Act: 2.0214. Min Act: -0.1700
Data Index: 6701055 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0719. Min Range: -2.0719
Max Act: 2.0214. Min Act: -0.1700
Data Index: 6983855 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9876. Min Act: -0.1700
Data Index: 3306616 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9876. Min Act: -0.1700
Data Index: 8583655 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9876. Min Act: -0.1700
Data Index: 5411757 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9876. Min Act: -0.1700
Data Index: 2953450 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0719. Min Range: -2.0719
Max Act: 2.0045. Min Act: -0.1700
Data Index: 7023887 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9707. Min Act: -0.1700
Data Index: 7549944 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9707. Min Act: -0.1700
Data Index: 1566218 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9707. Min Act: -0.1700
Data Index: 4151437 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9707. Min Act: -0.1700
Data Index: 6635724 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9707. Min Act: -0.1700
Data Index: 7354366 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9876. Min Act: -0.1700
Data Index: 4030018 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9707. Min Act: -0.1700
Data Index: 4982156 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0719. Min Range: -2.0719
Max Act: 1.9707. Min Act: -0.1700
Data Index: 7378341 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19