Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2035 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.9278. Min Act: -0.1700
Data Index: 2823506 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.8340. Min Act: -0.1658
Data Index: 8240363 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.8340. Min Act: -0.1700
Data Index: 6886141 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.7715. Min Act: -0.1700
Data Index: 6854123 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.7715. Min Act: -0.1700
Data Index: 8240357 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.7715. Min Act: -0.1700
Data Index: 5254264 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.7403. Min Act: -0.1700
Data Index: 7413167 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.7090. Min Act: -0.1700
Data Index: 2977758 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.7090. Min Act: -0.1700
Data Index: 6049083 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.6778. Min Act: -0.1700
Data Index: 2284512 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.6778. Min Act: -0.1700
Data Index: 1276636 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.6778. Min Act: -0.1700
Data Index: 3881258 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.6465. Min Act: -0.1689
Data Index: 2916395 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.6465. Min Act: -0.1700
Data Index: 7074730 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.6465. Min Act: -0.1700
Data Index: 5256210 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.6153. Min Act: -0.1700
Data Index: 3434672 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.6153. Min Act: -0.1700
Data Index: 5339808 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.6465. Min Act: -0.1700
Data Index: 6613454 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.6153. Min Act: -0.1700
Data Index: 7782142 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9278. Min Range: -5.9278
Max Act: 5.6153. Min Act: -0.1700
Data Index: 3953532 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19