Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4567 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.4566. Min Act: -0.1700
Data Index: 5039708 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3941. Min Act: -0.1700
Data Index: 477538 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3004. Min Act: -0.1700
Data Index: 8129149 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.2691. Min Act: -0.1700
Data Index: 6595054 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3004. Min Act: -0.1700
Data Index: 7157619 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.2691. Min Act: -0.1700
Data Index: 2404252 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.2379. Min Act: -0.1700
Data Index: 1283118 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.2379. Min Act: -0.1700
Data Index: 1878948 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.2379. Min Act: -0.1700
Data Index: 7982087 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.2379. Min Act: -0.1700
Data Index: 6221472 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.1754. Min Act: -0.1700
Data Index: 4271144 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.1754. Min Act: -0.1700
Data Index: 8115247 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.1129. Min Act: -0.1700
Data Index: 2276621 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.0816. Min Act: -0.1700
Data Index: 4966189 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.0816. Min Act: -0.1700
Data Index: 4643981 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.0816. Min Act: -0.1700
Data Index: 4184756 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.0816. Min Act: -0.1700
Data Index: 1603429 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.0816. Min Act: -0.1700
Data Index: 1181067 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.0504. Min Act: -0.1700
Data Index: 7553124 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.0504. Min Act: -0.1700
Data Index: 5126920 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19