Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5515 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2463. Min Range: -6.2463
Max Act: 6.2463. Min Act: -0.1700
Data Index: 3713785 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2463. Min Range: -6.2463
Max Act: 6.1838. Min Act: -0.1700
Data Index: 7219193 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2463. Min Range: -6.2463
Max Act: 6.1838. Min Act: -0.1700
Data Index: 3752455 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2463. Min Range: -6.2463
Max Act: 6.1838. Min Act: -0.1700
Data Index: 1931930 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2463. Min Range: -6.2463
Max Act: 6.0901. Min Act: -0.1700
Data Index: 734929 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2463. Min Range: -6.2463
Max Act: 6.0588. Min Act: -0.1700
Data Index: 7767313 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2463. Min Range: -6.2463
Max Act: 6.0276. Min Act: -0.1700
Data Index: 8618204 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2463. Min Range: -6.2463
Max Act: 6.0276. Min Act: -0.1700
Data Index: 7917568 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.9963. Min Act: -0.1700
Data Index: 7307916 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.9651. Min Act: -0.1700
Data Index: 4581941 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.9338. Min Act: -0.1700
Data Index: 7514167 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.9338. Min Act: -0.1700
Data Index: 1363068 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.9026. Min Act: -0.1700
Data Index: 1191903 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.9026. Min Act: -0.1700
Data Index: 695877 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.9026. Min Act: -0.1700
Data Index: 2193305 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.8713. Min Act: -0.1700
Data Index: 7129351 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.8713. Min Act: -0.1700
Data Index: 3696155 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.9026. Min Act: -0.1700
Data Index: 1688370 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.8713. Min Act: -0.1700
Data Index: 7989745 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2463. Min Range: -6.2463
Max Act: 5.8401. Min Act: -0.1700
Data Index: 4280783 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19