Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2746 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1301. Min Range: -6.1301
Max Act: 6.1301. Min Act: -0.1700
Data Index: 59413 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1301. Min Range: -6.1301
Max Act: 6.0989. Min Act: -0.1700
Data Index: 2261499 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1301. Min Range: -6.1301
Max Act: 6.0364. Min Act: -0.1700
Data Index: 1765708 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.9739. Min Act: -0.1700
Data Index: 2653806 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.9739. Min Act: -0.1700
Data Index: 3891195 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.9426. Min Act: -0.1700
Data Index: 6662238 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.9114. Min Act: -0.1700
Data Index: 7205984 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.9114. Min Act: -0.1700
Data Index: 988504 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.9114. Min Act: -0.1700
Data Index: 5370626 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.8801. Min Act: -0.1700
Data Index: 8827889 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.8176. Min Act: -0.1700
Data Index: 2257550 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.8489. Min Act: -0.1700
Data Index: 7200415 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.8489. Min Act: -0.1700
Data Index: 6283215 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.8176. Min Act: -0.1700
Data Index: 5793338 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.7864. Min Act: -0.1700
Data Index: 8496575 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.8176. Min Act: -0.1700
Data Index: 800483 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.7551. Min Act: -0.1700
Data Index: 3695353 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.7551. Min Act: -0.1700
Data Index: 3281588 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.7551. Min Act: -0.1700
Data Index: 1883785 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1301. Min Range: -6.1301
Max Act: 5.7551. Min Act: -0.1700
Data Index: 3664032 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19