Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 686 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3743. Min Range: -8.3743
Max Act: 8.3743. Min Act: -0.1700
Data Index: 7021325 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3743. Min Range: -8.3743
Max Act: 8.1868. Min Act: -0.1700
Data Index: 7485256 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3743. Min Range: -8.3743
Max Act: 8.0618. Min Act: -0.1700
Data Index: 2630134 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.9993. Min Act: -0.1700
Data Index: 1245133 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.9368. Min Act: -0.1700
Data Index: 3011486 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.9368. Min Act: -0.1700
Data Index: 6427767 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.8743. Min Act: -0.1700
Data Index: 7353129 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.9368. Min Act: -0.1700
Data Index: 1955408 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.8743. Min Act: -0.1700
Data Index: 4138081 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.8743. Min Act: -0.1700
Data Index: 6230806 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.8118. Min Act: -0.1700
Data Index: 5863012 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.7493. Min Act: -0.1700
Data Index: 7929203 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.7493. Min Act: -0.1700
Data Index: 8376619 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.7493. Min Act: -0.1700
Data Index: 5792571 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.8118. Min Act: -0.1700
Data Index: 1364532 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.7493. Min Act: -0.1700
Data Index: 4770886 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.6243. Min Act: -0.1700
Data Index: 6029702 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.6243. Min Act: -0.1700
Data Index: 3798486 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.6868. Min Act: -0.1700
Data Index: 6911975 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3743. Min Range: -8.3743
Max Act: 7.7493. Min Act: -0.1700
Data Index: 1898236 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19