Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.8405. Min Act: -0.1700
Data Index: 8460092 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.8092. Min Act: -0.1700
Data Index: 4999534 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.7936. Min Act: -0.1700
Data Index: 7300081 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.7623. Min Act: -0.1700
Data Index: 8715295 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6685. Min Act: -0.1700
Data Index: 52644 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6372. Min Act: -0.1700
Data Index: 3980790 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.7154. Min Act: -0.1700
Data Index: 4259490 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6998. Min Act: -0.1700
Data Index: 5077406 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6685. Min Act: -0.1700
Data Index: 5144670 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6841. Min Act: -0.1700
Data Index: 4832764 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6528. Min Act: -0.1700
Data Index: 3459171 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6528. Min Act: -0.1700
Data Index: 2535414 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6685. Min Act: -0.1700
Data Index: 6328893 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6528. Min Act: -0.1700
Data Index: 3011365 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6372. Min Act: -0.1700
Data Index: 4958687 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6215. Min Act: -0.1700
Data Index: 6170106 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6372. Min Act: -0.1700
Data Index: 3162797 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6059. Min Act: -0.1700
Data Index: 3267693 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.6215. Min Act: -0.1700
Data Index: 6920788 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8405. Min Range: -3.8405
Max Act: 3.5902. Min Act: -0.1700
Data Index: 811551 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19