Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2047 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.5619. Min Act: -0.1700
Data Index: 8743528 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.5463. Min Act: -0.1700
Data Index: 5719608 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.5619. Min Act: -0.1700
Data Index: 4546620 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.5150. Min Act: -0.1700
Data Index: 8678955 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4993. Min Act: -0.1700
Data Index: 4546621 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4836. Min Act: -0.1700
Data Index: 2078850 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4836. Min Act: -0.1700
Data Index: 6323548 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4523. Min Act: -0.1700
Data Index: 5390081 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4680. Min Act: -0.1700
Data Index: 2528455 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4523. Min Act: -0.1700
Data Index: 7188919 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4366. Min Act: -0.1700
Data Index: 3401966 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4523. Min Act: -0.1700
Data Index: 453928 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4523. Min Act: -0.1700
Data Index: 3596561 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4366. Min Act: -0.1700
Data Index: 3153817 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4523. Min Act: -0.1700
Data Index: 6255503 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4523. Min Act: -0.1700
Data Index: 6811914 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4366. Min Act: -0.1700
Data Index: 2234624 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4366. Min Act: -0.1700
Data Index: 7727165 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4366. Min Act: -0.1700
Data Index: 3833376 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4366. Min Act: -0.1700
Data Index: 7288552 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19