Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4448 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0741. Min Range: -3.0741
Max Act: 3.0741. Min Act: -0.1700
Data Index: 1814340 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9952. Min Act: -0.1700
Data Index: 638328 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9952. Min Act: -0.1700
Data Index: 7163089 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9952. Min Act: -0.1700
Data Index: 8416800 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9794. Min Act: -0.1700
Data Index: 7895531 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9794. Min Act: -0.1700
Data Index: 5716375 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9635. Min Act: -0.1697
Data Index: 9493 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9635. Min Act: -0.1700
Data Index: 1814338 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9319. Min Act: -0.1700
Data Index: 1387598 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9319. Min Act: -0.1700
Data Index: 8223507 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.8843. Min Act: -0.1700
Data Index: 290265 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.8526. Min Act: -0.1700
Data Index: 8495541 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.8843. Min Act: -0.1700
Data Index: 8131554 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.8684. Min Act: -0.1700
Data Index: 6476230 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.8526. Min Act: -0.1700
Data Index: 3131785 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.8208. Min Act: -0.1700
Data Index: 7045232 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.8208. Min Act: -0.1700
Data Index: 5071868 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.8367. Min Act: -0.1700
Data Index: 1942961 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.8367. Min Act: -0.1700
Data Index: 5027812 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.8367. Min Act: -0.1700
Data Index: 8113108 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19