Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4880 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0825. Min Range: -4.0825
Max Act: 4.0825. Min Act: -0.1700
Data Index: 6858546 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0825. Min Range: -4.0825
Max Act: 4.0513. Min Act: -0.1700
Data Index: 1387538 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0825. Min Range: -4.0825
Max Act: 4.0200. Min Act: -0.1700
Data Index: 1275434 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0825. Min Range: -4.0825
Max Act: 4.0200. Min Act: -0.1700
Data Index: 2523737 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.9575. Min Act: -0.1700
Data Index: 699157 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.9575. Min Act: -0.1700
Data Index: 7172427 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.9262. Min Act: -0.1700
Data Index: 3721506 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.9262. Min Act: -0.1700
Data Index: 8069889 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.9575. Min Act: -0.1700
Data Index: 6208931 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.8793. Min Act: -0.1700
Data Index: 2734726 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.8793. Min Act: -0.1700
Data Index: 2993693 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.8793. Min Act: -0.1700
Data Index: 245481 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.8637. Min Act: -0.1700
Data Index: 5101070 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.8481. Min Act: -0.1700
Data Index: 7592393 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.8481. Min Act: -0.1700
Data Index: 7697505 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.8168. Min Act: -0.1700
Data Index: 3373927 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.8324. Min Act: -0.1700
Data Index: 1569305 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.8168. Min Act: -0.1700
Data Index: 3764931 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.8011. Min Act: -0.1700
Data Index: 5111636 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0825. Min Range: -4.0825
Max Act: 3.7855. Min Act: -0.1700
Data Index: 2307406 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19