Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4854 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1496. Min Range: -5.1496
Max Act: 5.1496. Min Act: -0.1700
Data Index: 8410210 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1496. Min Range: -5.1496
Max Act: 5.1496. Min Act: -0.1700
Data Index: 7597341 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1496. Min Range: -5.1496
Max Act: 5.1183. Min Act: -0.1700
Data Index: 8389687 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1496. Min Range: -5.1496
Max Act: 5.0871. Min Act: -0.1700
Data Index: 2257608 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1496. Min Range: -5.1496
Max Act: 5.0558. Min Act: -0.1700
Data Index: 8228574 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.8996. Min Act: -0.1700
Data Index: 4265404 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.8371. Min Act: -0.1700
Data Index: 1483946 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.8683. Min Act: -0.1700
Data Index: 4105942 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.8683. Min Act: -0.1700
Data Index: 4708318 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.8371. Min Act: -0.1700
Data Index: 1378211 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.8371. Min Act: -0.1700
Data Index: 6393157 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.8058. Min Act: -0.1700
Data Index: 4981357 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.8058. Min Act: -0.1700
Data Index: 5759191 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.7746. Min Act: -0.1700
Data Index: 4449750 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.7746. Min Act: -0.1700
Data Index: 3202205 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.7746. Min Act: -0.1700
Data Index: 708710 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.8058. Min Act: -0.1700
Data Index: 4092095 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.7746. Min Act: -0.1700
Data Index: 8045443 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.7746. Min Act: -0.1700
Data Index: 1672400 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.7433. Min Act: -0.1700
Data Index: 6895129 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19