Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5184. Min Range: -6.5184
Max Act: 6.5184. Min Act: -0.1700
Data Index: 2260360 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5184. Min Range: -6.5184
Max Act: 6.4559. Min Act: -0.1700
Data Index: 1665575 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5184. Min Range: -6.5184
Max Act: 6.2372. Min Act: -0.1700
Data Index: 5133857 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5184. Min Range: -6.5184
Max Act: 6.2059. Min Act: -0.1700
Data Index: 7336863 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5184. Min Range: -6.5184
Max Act: 6.0809. Min Act: -0.1700
Data Index: 7503254 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.9872. Min Act: -0.1700
Data Index: 8574559 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.8934. Min Act: -0.1700
Data Index: 4722843 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.9247. Min Act: -0.1700
Data Index: 1969325 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.9559. Min Act: -0.1700
Data Index: 696773 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.9247. Min Act: -0.1700
Data Index: 7042089 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.9247. Min Act: -0.1700
Data Index: 123279 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.8934. Min Act: -0.1700
Data Index: 2930652 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.8934. Min Act: -0.1700
Data Index: 5879098 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.7997. Min Act: -0.1700
Data Index: 8200999 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.7997. Min Act: -0.1700
Data Index: 898582 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.7684. Min Act: -0.1700
Data Index: 5470927 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.7684. Min Act: -0.1700
Data Index: 5686250 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.7684. Min Act: -0.1700
Data Index: 6239582 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.7372. Min Act: -0.1700
Data Index: 4431919 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5184. Min Range: -6.5184
Max Act: 5.7059. Min Act: -0.1700
Data Index: 1443231 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19