Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1382 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0517. Min Range: -6.0517
Max Act: 6.0517. Min Act: -0.1700
Data Index: 3685466 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.9892. Min Act: -0.1700
Data Index: 4185695 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.9892. Min Act: -0.1700
Data Index: 225154 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0517. Min Range: -6.0517
Max Act: 6.0204. Min Act: -0.1700
Data Index: 252247 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.9579. Min Act: -0.1700
Data Index: 3746742 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.9267. Min Act: -0.1700
Data Index: 4936563 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.9267. Min Act: -0.1700
Data Index: 650195 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.9267. Min Act: -0.1700
Data Index: 3654810 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.8642. Min Act: -0.1700
Data Index: 5373956 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.8329. Min Act: -0.1700
Data Index: 3685467 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.8642. Min Act: -0.1700
Data Index: 5589962 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.8642. Min Act: -0.1700
Data Index: 4058216 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.8954. Min Act: -0.1700
Data Index: 4276353 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.8329. Min Act: -0.1700
Data Index: 5064540 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.8017. Min Act: -0.1700
Data Index: 4276352 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.7704. Min Act: -0.1700
Data Index: 2120466 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.7392. Min Act: -0.1700
Data Index: 252248 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.7704. Min Act: -0.1700
Data Index: 8025455 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.7392. Min Act: -0.1700
Data Index: 650196 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0517. Min Range: -6.0517
Max Act: 5.7392. Min Act: -0.1700
Data Index: 2120467 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19