Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3251 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0936. Min Range: -5.0936
Max Act: 5.0624. Min Act: -0.1700
Data Index: 3598142 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0936. Min Range: -5.0936
Max Act: 5.0936. Min Act: -0.1700
Data Index: 2650285 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0936. Min Range: -5.0936
Max Act: 5.0624. Min Act: -0.1700
Data Index: 2433571 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0936. Min Range: -5.0936
Max Act: 5.0311. Min Act: -0.1700
Data Index: 3356958 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0936. Min Range: -5.0936
Max Act: 5.0311. Min Act: -0.1700
Data Index: 2526103 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.9686. Min Act: -0.1700
Data Index: 8573814 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.9374. Min Act: -0.1700
Data Index: 748546 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.9686. Min Act: -0.1700
Data Index: 3010253 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.9374. Min Act: -0.1700
Data Index: 1874617 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.9374. Min Act: -0.1700
Data Index: 4235905 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.9061. Min Act: -0.1700
Data Index: 5642899 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.9061. Min Act: -0.1700
Data Index: 911695 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.9061. Min Act: -0.1700
Data Index: 7579126 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.8749. Min Act: -0.1700
Data Index: 89711 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.9061. Min Act: -0.1700
Data Index: 7977428 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.8749. Min Act: -0.1700
Data Index: 5002540 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.8749. Min Act: -0.1700
Data Index: 3319249 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.8436. Min Act: -0.1700
Data Index: 2312663 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.8749. Min Act: -0.1700
Data Index: 6573296 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0936. Min Range: -5.0936
Max Act: 4.8749. Min Act: -0.1700
Data Index: 1468706 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19