Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5392 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.7819. Min Act: -0.1700
Data Index: 8425106 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.4069. Min Act: -0.1700
Data Index: 714289 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.3444. Min Act: -0.1700
Data Index: 7402579 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.3131. Min Act: -0.1700
Data Index: 222496 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.0944. Min Act: -0.1700
Data Index: 5747196 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.0631. Min Act: -0.1700
Data Index: 861323 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.0631. Min Act: -0.1700
Data Index: 4046507 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.0631. Min Act: -0.1700
Data Index: 5767520 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.0319. Min Act: -0.1700
Data Index: 753065 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.0006. Min Act: -0.1700
Data Index: 7975564 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.0006. Min Act: -0.1700
Data Index: 2822487 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7819. Min Range: -6.7819
Max Act: 6.0006. Min Act: -0.1700
Data Index: 8677349 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7819. Min Range: -6.7819
Max Act: 5.9694. Min Act: -0.1700
Data Index: 5695508 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7819. Min Range: -6.7819
Max Act: 5.9381. Min Act: -0.1700
Data Index: 3291109 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7819. Min Range: -6.7819
Max Act: 5.9069. Min Act: -0.1700
Data Index: 5426758 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7819. Min Range: -6.7819
Max Act: 5.8756. Min Act: -0.1700
Data Index: 6701291 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7819. Min Range: -6.7819
Max Act: 5.8444. Min Act: -0.1700
Data Index: 3762417 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7819. Min Range: -6.7819
Max Act: 5.8444. Min Act: -0.1700
Data Index: 2231935 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7819. Min Range: -6.7819
Max Act: 5.8444. Min Act: -0.1700
Data Index: 6513790 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7819. Min Range: -6.7819
Max Act: 5.8444. Min Act: -0.1700
Data Index: 1712526 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19