Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 942 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.5559. Min Act: -0.1700
Data Index: 2278175 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.2434. Min Act: -0.1700
Data Index: 4313650 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.2122. Min Act: -0.1700
Data Index: 1890554 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.1184. Min Act: -0.1700
Data Index: 860817 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.1184. Min Act: -0.1700
Data Index: 1203620 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.0872. Min Act: -0.1700
Data Index: 8399986 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.0559. Min Act: -0.1700
Data Index: 6259863 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.0559. Min Act: -0.1700
Data Index: 508697 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.0559. Min Act: -0.1700
Data Index: 1890561 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5559. Min Range: -7.5559
Max Act: 6.9934. Min Act: -0.1700
Data Index: 2713916 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.0559. Min Act: -0.1700
Data Index: 6808396 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.0247. Min Act: -0.1700
Data Index: 4051297 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5559. Min Range: -7.5559
Max Act: 6.9934. Min Act: -0.1700
Data Index: 5012140 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5559. Min Range: -7.5559
Max Act: 6.9934. Min Act: -0.1700
Data Index: 8167873 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5559. Min Range: -7.5559
Max Act: 6.9934. Min Act: -0.1700
Data Index: 7327054 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.0247. Min Act: -0.1700
Data Index: 269807 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.0247. Min Act: -0.1700
Data Index: 6884265 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5559. Min Range: -7.5559
Max Act: 6.9622. Min Act: -0.1700
Data Index: 5469883 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5559. Min Range: -7.5559
Max Act: 6.9622. Min Act: -0.1700
Data Index: 4057635 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5559. Min Range: -7.5559
Max Act: 6.9309. Min Act: -0.1700
Data Index: 1291421 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19