Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4017. Min Range: -5.4017
Max Act: 5.4017. Min Act: -0.1700
Data Index: 2547812 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4017. Min Range: -5.4017
Max Act: 5.3392. Min Act: -0.1700
Data Index: 3480408 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4017. Min Range: -5.4017
Max Act: 5.3705. Min Act: -0.1700
Data Index: 4913423 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4017. Min Range: -5.4017
Max Act: 5.2455. Min Act: -0.1700
Data Index: 2251087 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.9642. Min Act: -0.1700
Data Index: 8816790 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.8392. Min Act: -0.1700
Data Index: 4322018 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.8392. Min Act: -0.1700
Data Index: 5317255 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.7767. Min Act: -0.1700
Data Index: 4075661 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.7767. Min Act: -0.1700
Data Index: 1016670 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.7767. Min Act: -0.1700
Data Index: 5939112 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.7767. Min Act: -0.1700
Data Index: 3531178 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.7142. Min Act: -0.1700
Data Index: 2447652 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.7142. Min Act: -0.1700
Data Index: 4507494 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.6830. Min Act: -0.1700
Data Index: 8611047 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.6830. Min Act: -0.1700
Data Index: 1766427 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.6830. Min Act: -0.1700
Data Index: 2195339 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.6830. Min Act: -0.1700
Data Index: 2571482 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.6517. Min Act: -0.1700
Data Index: 3669929 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.6517. Min Act: -0.1700
Data Index: 5018703 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4017. Min Range: -5.4017
Max Act: 4.6205. Min Act: -0.1700
Data Index: 4281119 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19