Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1870 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.3232. Min Act: -0.1700
Data Index: 6437080 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.3857. Min Act: -0.1700
Data Index: 7622782 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.3544. Min Act: -0.1700
Data Index: 3048996 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1982. Min Act: -0.1700
Data Index: 5706388 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.2294. Min Act: -0.1700
Data Index: 4380412 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.2294. Min Act: -0.1700
Data Index: 7285772 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1669. Min Act: -0.1700
Data Index: 3869739 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1669. Min Act: -0.1700
Data Index: 6819621 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1669. Min Act: -0.1700
Data Index: 6890314 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.2294. Min Act: -0.1700
Data Index: 6908006 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1669. Min Act: -0.1700
Data Index: 2810636 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1669. Min Act: -0.1700
Data Index: 1323230 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1357. Min Act: -0.1700
Data Index: 6259960 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1982. Min Act: -0.1700
Data Index: 3810908 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1669. Min Act: -0.1700
Data Index: 6696684 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1357. Min Act: -0.1700
Data Index: 1713907 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1357. Min Act: -0.1700
Data Index: 6784303 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.1044. Min Act: -0.1700
Data Index: 7771352 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.0732. Min Act: -0.1700
Data Index: 1287105 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3857. Min Range: -5.3857
Max Act: 5.0732. Min Act: -0.1700
Data Index: 6349468 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19