Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.4595. Min Act: -0.1700
Data Index: 8007933 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.3658. Min Act: -0.1700
Data Index: 6018939 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.3658. Min Act: -0.1700
Data Index: 687628 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.3658. Min Act: -0.1700
Data Index: 1188130 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.3345. Min Act: -0.1700
Data Index: 5948982 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.2095. Min Act: -0.1700
Data Index: 3255299 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.1783. Min Act: -0.1700
Data Index: 8381442 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.1470. Min Act: -0.1700
Data Index: 5900786 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.1470. Min Act: -0.1700
Data Index: 545556 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.1158. Min Act: -0.1700
Data Index: 506739 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.0533. Min Act: -0.1700
Data Index: 2462809 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.0533. Min Act: -0.1700
Data Index: 5808839 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.0220. Min Act: -0.1700
Data Index: 6063077 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.0220. Min Act: -0.1700
Data Index: 4306428 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.0220. Min Act: -0.1700
Data Index: 5004630 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.0533. Min Act: -0.1700
Data Index: 704532 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.0220. Min Act: -0.1700
Data Index: 3382850 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4595. Min Range: -6.4595
Max Act: 6.0220. Min Act: -0.1700
Data Index: 875720 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4595. Min Range: -6.4595
Max Act: 5.9908. Min Act: -0.1700
Data Index: 4089596 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4595. Min Range: -6.4595
Max Act: 5.9595. Min Act: -0.1700
Data Index: 4567153 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19