Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4878 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.9153. Min Act: -0.1700
Data Index: 472807 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.7278. Min Act: -0.1700
Data Index: 2098034 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.7278. Min Act: -0.1700
Data Index: 7461352 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.6653. Min Act: -0.1700
Data Index: 2379927 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.7278. Min Act: -0.1700
Data Index: 3818916 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.6653. Min Act: -0.1700
Data Index: 2120192 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.6028. Min Act: -0.1700
Data Index: 8139276 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.6028. Min Act: -0.1700
Data Index: 1963825 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.6028. Min Act: -0.1700
Data Index: 195196 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.4778. Min Act: -0.1700
Data Index: 1871547 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.4778. Min Act: -0.1700
Data Index: 4536564 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.4778. Min Act: -0.1700
Data Index: 3596394 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.4778. Min Act: -0.1700
Data Index: 6173872 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.4153. Min Act: -0.1700
Data Index: 2465506 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.4153. Min Act: -0.1700
Data Index: 741240 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.4153. Min Act: -0.1700
Data Index: 4802076 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.4778. Min Act: -0.1700
Data Index: 2647622 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.4153. Min Act: -0.1700
Data Index: 7577258 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.4153. Min Act: -0.1700
Data Index: 7317655 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9153. Min Range: -8.9153
Max Act: 8.4153. Min Act: -0.1700
Data Index: 2497703 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19