Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 232 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3604. Min Range: -7.3604
Max Act: 7.3604. Min Act: -0.1700
Data Index: 3691312 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.9542. Min Act: -0.1700
Data Index: 4269894 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.8292. Min Act: -0.1700
Data Index: 8353035 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.7042. Min Act: -0.1700
Data Index: 6080076 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.6729. Min Act: -0.1700
Data Index: 1162934 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.6729. Min Act: -0.1700
Data Index: 1551745 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.6729. Min Act: -0.1700
Data Index: 2525822 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.6729. Min Act: -0.1700
Data Index: 2595849 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.6104. Min Act: -0.1700
Data Index: 8521208 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.6104. Min Act: -0.1700
Data Index: 3463707 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.6104. Min Act: -0.1700
Data Index: 6461643 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.6104. Min Act: -0.1700
Data Index: 4986902 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.6417. Min Act: -0.1700
Data Index: 1704749 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.6104. Min Act: -0.1700
Data Index: 759551 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.5792. Min Act: -0.1700
Data Index: 2263622 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.5792. Min Act: -0.1700
Data Index: 552754 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.5479. Min Act: -0.1700
Data Index: 7091909 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.5167. Min Act: -0.1700
Data Index: 6840640 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.5167. Min Act: -0.1700
Data Index: 5325996 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3604. Min Range: -7.3604
Max Act: 6.5167. Min Act: -0.1700
Data Index: 6217749 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19