Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.6384. Min Act: -0.1700
Data Index: 5623348 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.6071. Min Act: -0.1700
Data Index: 4413709 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.4509. Min Act: -0.1700
Data Index: 3217899 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.4821. Min Act: -0.1700
Data Index: 7978521 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.4821. Min Act: -0.1700
Data Index: 130265 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.4821. Min Act: -0.1700
Data Index: 4061440 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.4509. Min Act: -0.1700
Data Index: 4869818 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.3571. Min Act: -0.1700
Data Index: 864591 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.3884. Min Act: -0.1700
Data Index: 5883576 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.3884. Min Act: -0.1700
Data Index: 8722005 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.3571. Min Act: -0.1700
Data Index: 8666344 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.3259. Min Act: -0.1700
Data Index: 610295 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.2946. Min Act: -0.1700
Data Index: 2616369 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.2946. Min Act: -0.1700
Data Index: 4852136 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.2634. Min Act: -0.1700
Data Index: 130247 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.2634. Min Act: -0.1700
Data Index: 3347902 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.2946. Min Act: -0.1700
Data Index: 7415354 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.2634. Min Act: -0.1700
Data Index: 7614007 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.2321. Min Act: -0.1700
Data Index: 4032459 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6384. Min Range: -7.6384
Max Act: 7.1696. Min Act: -0.1700
Data Index: 4981314 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19