Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 523 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.6579. Min Act: -0.1700
Data Index: 8228303 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.5016. Min Act: -0.1700
Data Index: 7008166 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.5016. Min Act: -0.1700
Data Index: 2234367 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.4704. Min Act: -0.1700
Data Index: 357508 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.4079. Min Act: -0.1700
Data Index: 6490400 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.4079. Min Act: -0.1700
Data Index: 7162966 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.3766. Min Act: -0.1700
Data Index: 7290843 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.0954. Min Act: -0.1700
Data Index: 8598306 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.0329. Min Act: -0.1700
Data Index: 5945641 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.0641. Min Act: -0.1700
Data Index: 5200856 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.0641. Min Act: -0.1700
Data Index: 2079466 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.0329. Min Act: -0.1700
Data Index: 7760264 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6579. Min Range: -7.6579
Max Act: 6.9704. Min Act: -0.1700
Data Index: 8055928 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6579. Min Range: -7.6579
Max Act: 6.9704. Min Act: -0.1700
Data Index: 6547842 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6579. Min Range: -7.6579
Max Act: 6.9704. Min Act: -0.1700
Data Index: 1582662 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6579. Min Range: -7.6579
Max Act: 7.0016. Min Act: -0.1700
Data Index: 2953253 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6579. Min Range: -7.6579
Max Act: 6.9079. Min Act: -0.1700
Data Index: 541694 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6579. Min Range: -7.6579
Max Act: 6.9391. Min Act: -0.1700
Data Index: 8417692 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6579. Min Range: -7.6579
Max Act: 6.9079. Min Act: -0.1700
Data Index: 3588735 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6579. Min Range: -7.6579
Max Act: 6.9391. Min Act: -0.1700
Data Index: 8543486 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19