Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.8153. Min Act: -0.1700
Data Index: 4648506 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.7840. Min Act: -0.1700
Data Index: 7650648 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.7683. Min Act: -0.1700
Data Index: 6248603 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.7527. Min Act: -0.1700
Data Index: 2499704 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.7371. Min Act: -0.1700
Data Index: 4051204 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.7214. Min Act: -0.1700
Data Index: 3371602 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.7214. Min Act: -0.1700
Data Index: 1666259 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6901. Min Act: -0.1700
Data Index: 7179459 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6901. Min Act: -0.1700
Data Index: 4111564 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6745. Min Act: -0.1700
Data Index: 1456019 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6745. Min Act: -0.1700
Data Index: 1949695 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6745. Min Act: -0.1700
Data Index: 8421279 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6745. Min Act: -0.1700
Data Index: 3583789 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6432. Min Act: -0.1700
Data Index: 4487462 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6745. Min Act: -0.1700
Data Index: 1777086 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6432. Min Act: -0.1700
Data Index: 786635 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6432. Min Act: -0.1700
Data Index: 2892865 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6432. Min Act: -0.1700
Data Index: 8534657 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6119. Min Act: -0.1700
Data Index: 4439827 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8153. Min Range: -3.8153
Max Act: 3.6119. Min Act: -0.1700
Data Index: 6532833 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19