Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2429 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5605. Min Range: -11.5605
Max Act: 11.5605. Min Act: -0.1700
Data Index: 358064 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5605. Min Range: -11.5605
Max Act: 11.4980. Min Act: -0.1700
Data Index: 935099 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.9355. Min Act: -0.1700
Data Index: 7791411 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.8105. Min Act: -0.1700
Data Index: 828243 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.4980. Min Act: -0.1697
Data Index: 3895149 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.4980. Min Act: -0.1700
Data Index: 2040938 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.4355. Min Act: -0.1699
Data Index: 3130827 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.3105. Min Act: -0.1700
Data Index: 8108612 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.3105. Min Act: -0.1700
Data Index: 4117363 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.2480. Min Act: -0.1700
Data Index: 8189844 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.3105. Min Act: -0.1700
Data Index: 1078966 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.1855. Min Act: -0.1700
Data Index: 427879 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.1230. Min Act: -0.1700
Data Index: 5832532 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.0605. Min Act: -0.1697
Data Index: 6428528 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.0605. Min Act: -0.1698
Data Index: 4350871 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5605. Min Range: -11.5605
Max Act: 10.0605. Min Act: -0.1700
Data Index: 3472974 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5605. Min Range: -11.5605
Max Act: 9.9980. Min Act: -0.1694
Data Index: 4117371 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5605. Min Range: -11.5605
Max Act: 9.9980. Min Act: -0.1700
Data Index: 3457077 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5605. Min Range: -11.5605
Max Act: 9.9355. Min Act: -0.1700
Data Index: 6981089 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5605. Min Range: -11.5605
Max Act: 9.9355. Min Act: -0.1700
Data Index: 7970687 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19