Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 796 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1591. Min Range: -4.1591
Max Act: 4.1591. Min Act: -0.1700
Data Index: 8159645 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1591. Min Range: -4.1591
Max Act: 4.1591. Min Act: -0.1700
Data Index: 6798304 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1591. Min Range: -4.1591
Max Act: 4.1591. Min Act: -0.1700
Data Index: 4098372 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1591. Min Range: -4.1591
Max Act: 4.1278. Min Act: -0.1700
Data Index: 5212703 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1591. Min Range: -4.1591
Max Act: 4.0653. Min Act: -0.1700
Data Index: 1674262 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1591. Min Range: -4.1591
Max Act: 4.0653. Min Act: -0.1700
Data Index: 1648372 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.9871. Min Act: -0.1700
Data Index: 2141514 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1591. Min Range: -4.1591
Max Act: 4.0184. Min Act: -0.1700
Data Index: 5949033 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1591. Min Range: -4.1591
Max Act: 4.0340. Min Act: -0.1700
Data Index: 5373898 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.9871. Min Act: -0.1700
Data Index: 5027127 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.9559. Min Act: -0.1700
Data Index: 2600852 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.9559. Min Act: -0.1700
Data Index: 8036192 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.9402. Min Act: -0.1700
Data Index: 6436676 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.9246. Min Act: -0.1700
Data Index: 8097746 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.9559. Min Act: -0.1700
Data Index: 1971219 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.9246. Min Act: -0.1700
Data Index: 6578251 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.9090. Min Act: -0.1700
Data Index: 1180147 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.9246. Min Act: -0.1700
Data Index: 1549098 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.8933. Min Act: -0.1700
Data Index: 3596023 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1591. Min Range: -4.1591
Max Act: 3.9090. Min Act: -0.1700
Data Index: 2261639 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19