Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 291 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.8448. Min Act: -0.1700
Data Index: 1886644 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.8448. Min Act: -0.1700
Data Index: 1708049 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.7823. Min Act: -0.1700
Data Index: 6013653 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.6261. Min Act: -0.1700
Data Index: 2040524 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5948. Min Act: -0.1700
Data Index: 8722235 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5948. Min Act: -0.1700
Data Index: 921664 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5636. Min Act: -0.1700
Data Index: 6095953 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5636. Min Act: -0.1700
Data Index: 4345806 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5323. Min Act: -0.1700
Data Index: 1584101 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5323. Min Act: -0.1700
Data Index: 3825948 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5323. Min Act: -0.1700
Data Index: 261388 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5323. Min Act: -0.1700
Data Index: 6817850 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5011. Min Act: -0.1700
Data Index: 3788788 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4698. Min Act: -0.1700
Data Index: 5452318 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4698. Min Act: -0.1700
Data Index: 2529153 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4698. Min Act: -0.1700
Data Index: 7726428 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4698. Min Act: -0.1700
Data Index: 7712693 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4386. Min Act: -0.1700
Data Index: 7886183 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4386. Min Act: -0.1700
Data Index: 2033334 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4698. Min Act: -0.1700
Data Index: 3535110 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19