Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4434 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0407. Min Range: -4.0407
Max Act: 4.0407. Min Act: -0.1700
Data Index: 5798682 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0407. Min Range: -4.0407
Max Act: 4.0095. Min Act: -0.1700
Data Index: 8179531 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.9469. Min Act: -0.1700
Data Index: 586810 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.9469. Min Act: -0.1700
Data Index: 6128577 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.8531. Min Act: -0.1700
Data Index: 4364867 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.8219. Min Act: -0.1700
Data Index: 7463153 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.8531. Min Act: -0.1700
Data Index: 6506221 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.8219. Min Act: -0.1700
Data Index: 5407387 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.8219. Min Act: -0.1700
Data Index: 2147063 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.8219. Min Act: -0.1700
Data Index: 6939546 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.8219. Min Act: -0.1700
Data Index: 8152772 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.7906. Min Act: -0.1700
Data Index: 1567569 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.7906. Min Act: -0.1695
Data Index: 2867236 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.7593. Min Act: -0.1700
Data Index: 7306256 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.7593. Min Act: -0.1700
Data Index: 4038155 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.7593. Min Act: -0.1700
Data Index: 1034454 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.6655. Min Act: -0.1700
Data Index: 4142865 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.6967. Min Act: -0.1700
Data Index: 8649549 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.6655. Min Act: -0.1700
Data Index: 5908491 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0407. Min Range: -4.0407
Max Act: 3.6655. Min Act: -0.1700
Data Index: 3858170 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19