Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2352 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.9122. Min Act: -0.1700
Data Index: 2752052 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8964. Min Act: -0.1700
Data Index: 2205340 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8805. Min Act: -0.1700
Data Index: 3591967 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8488. Min Act: -0.1700
Data Index: 1404705 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8488. Min Act: -0.1700
Data Index: 3233962 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8488. Min Act: -0.1700
Data Index: 3779583 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8488. Min Act: -0.1700
Data Index: 3815337 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8170. Min Act: -0.1700
Data Index: 3671187 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8170. Min Act: -0.1700
Data Index: 7178242 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8170. Min Act: -0.1700
Data Index: 2183978 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8170. Min Act: -0.1700
Data Index: 946249 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8170. Min Act: -0.1700
Data Index: 7469205 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8170. Min Act: -0.1700
Data Index: 6149689 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8170. Min Act: -0.1700
Data Index: 5661937 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8010. Min Act: -0.1700
Data Index: 5168556 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8010. Min Act: -0.1700
Data Index: 3456315 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8010. Min Act: -0.1700
Data Index: 5378668 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8010. Min Act: -0.1700
Data Index: 6799187 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.8010. Min Act: -0.1700
Data Index: 1531329 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9122. Min Range: -2.9122
Max Act: 2.7851. Min Act: -0.1700
Data Index: 1325892 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19