Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3924 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1065. Min Range: -7.1065
Max Act: 7.1065. Min Act: -0.1700
Data Index: 2893139 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1065. Min Range: -7.1065
Max Act: 7.0440. Min Act: -0.1700
Data Index: 8591626 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.9502. Min Act: -0.1700
Data Index: 2955469 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.9502. Min Act: -0.1700
Data Index: 7334898 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.9815. Min Act: -0.1700
Data Index: 89672 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.9502. Min Act: -0.1700
Data Index: 5855964 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.8252. Min Act: -0.1700
Data Index: 7259947 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.7940. Min Act: -0.1700
Data Index: 2030112 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.8565. Min Act: -0.1700
Data Index: 1672993 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.7315. Min Act: -0.1700
Data Index: 1169733 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.7627. Min Act: -0.1700
Data Index: 5494961 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.7627. Min Act: -0.1700
Data Index: 5674583 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.6690. Min Act: -0.1700
Data Index: 2495422 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.6690. Min Act: -0.1700
Data Index: 6049777 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.7002. Min Act: -0.1700
Data Index: 6750614 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.7002. Min Act: -0.1700
Data Index: 3068665 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.6690. Min Act: -0.1700
Data Index: 4078583 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.7002. Min Act: -0.1700
Data Index: 6524185 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.6690. Min Act: -0.1700
Data Index: 5213447 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1065. Min Range: -7.1065
Max Act: 6.6377. Min Act: -0.1700
Data Index: 7971973 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19