Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2165 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.6767. Min Act: -0.1700
Data Index: 4752299 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.6419. Min Act: -0.1700
Data Index: 7541595 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5895. Min Act: -0.1700
Data Index: 4890497 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5808. Min Act: -0.1677
Data Index: 5709894 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5720. Min Act: -0.1700
Data Index: 5456147 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5633. Min Act: -0.1700
Data Index: 2445025 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5545. Min Act: -0.1696
Data Index: 6222452 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5545. Min Act: -0.1700
Data Index: 7456359 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5458. Min Act: -0.1700
Data Index: 3414397 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5370. Min Act: -0.1700
Data Index: 1887895 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5370. Min Act: -0.1689
Data Index: 5653033 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5370. Min Act: -0.1697
Data Index: 5046217 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5195. Min Act: -0.1700
Data Index: 1519993 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5195. Min Act: -0.1696
Data Index: 5046218 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5195. Min Act: -0.1700
Data Index: 7378839 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5283. Min Act: -0.1695
Data Index: 4053201 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5019. Min Act: -0.1698
Data Index: 5703016 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5019. Min Act: -0.1692
Data Index: 3786572 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5107. Min Act: -0.1700
Data Index: 887472 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6767. Min Range: -1.6767
Max Act: 1.5107. Min Act: -0.1660
Data Index: 7017990 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19