Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1410 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.8014. Min Act: -0.1700
Data Index: 2837617 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.6139. Min Act: -0.1700
Data Index: 5029071 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.6139. Min Act: -0.1700
Data Index: 5980277 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.6139. Min Act: -0.1700
Data Index: 6442725 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.4889. Min Act: -0.1700
Data Index: 8800942 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.4264. Min Act: -0.1700
Data Index: 7679269 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.4264. Min Act: -0.1700
Data Index: 6773391 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.4264. Min Act: -0.1700
Data Index: 2427356 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.4264. Min Act: -0.1700
Data Index: 318274 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.4264. Min Act: -0.1700
Data Index: 2781999 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.3639. Min Act: -0.1700
Data Index: 981150 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.3639. Min Act: -0.1700
Data Index: 7098293 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.4264. Min Act: -0.1700
Data Index: 1747769 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.3639. Min Act: -0.1700
Data Index: 1029839 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.3639. Min Act: -0.1700
Data Index: 431981 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.3639. Min Act: -0.1700
Data Index: 7193595 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.3639. Min Act: -0.1700
Data Index: 7191857 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.3639. Min Act: -0.1700
Data Index: 6327862 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.3014. Min Act: -0.1700
Data Index: 1244418 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8014. Min Range: -8.8014
Max Act: 8.3014. Min Act: -0.1700
Data Index: 7185890 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19