Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5581 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0784. Min Range: -6.0784
Max Act: 6.0784. Min Act: -0.1700
Data Index: 13806 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0784. Min Range: -6.0784
Max Act: 6.0472. Min Act: -0.1700
Data Index: 4242582 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.9847. Min Act: -0.1700
Data Index: 466373 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.9847. Min Act: -0.1700
Data Index: 8619352 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.9222. Min Act: -0.1700
Data Index: 1640988 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.9847. Min Act: -0.1700
Data Index: 7104322 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.9222. Min Act: -0.1700
Data Index: 2096270 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.9222. Min Act: -0.1700
Data Index: 2634594 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.9222. Min Act: -0.1700
Data Index: 8011939 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.8909. Min Act: -0.1700
Data Index: 7022348 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.8909. Min Act: -0.1700
Data Index: 652996 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.8597. Min Act: -0.1700
Data Index: 6659201 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.8597. Min Act: -0.1700
Data Index: 4829038 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.8597. Min Act: -0.1700
Data Index: 4403055 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.8597. Min Act: -0.1700
Data Index: 2107190 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.8597. Min Act: -0.1700
Data Index: 5955676 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.8597. Min Act: -0.1700
Data Index: 3452736 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.8597. Min Act: -0.1700
Data Index: 1152773 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.8597. Min Act: -0.1700
Data Index: 4839502 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0784. Min Range: -6.0784
Max Act: 5.8284. Min Act: -0.1700
Data Index: 7382478 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19