Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5141 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1364. Min Range: -8.1364
Max Act: 8.1364. Min Act: -0.1700
Data Index: 4596813 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.9489. Min Act: -0.1700
Data Index: 7545146 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.8552. Min Act: -0.1700
Data Index: 5333480 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.8239. Min Act: -0.1700
Data Index: 4456868 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7927. Min Act: -0.1700
Data Index: 6316886 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7927. Min Act: -0.1700
Data Index: 7399329 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7927. Min Act: -0.1700
Data Index: 7521087 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7927. Min Act: -0.1700
Data Index: 1938153 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7927. Min Act: -0.1700
Data Index: 1742378 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7614. Min Act: -0.1700
Data Index: 5871692 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7614. Min Act: -0.1700
Data Index: 517997 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7614. Min Act: -0.1700
Data Index: 7818146 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7614. Min Act: -0.1697
Data Index: 5400893 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7302. Min Act: -0.1700
Data Index: 655981 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7302. Min Act: -0.1700
Data Index: 707899 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7302. Min Act: -0.1700
Data Index: 5433251 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7302. Min Act: -0.1700
Data Index: 375878 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7302. Min Act: -0.1700
Data Index: 1237486 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.7302. Min Act: -0.1700
Data Index: 3482337 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1364. Min Range: -8.1364
Max Act: 7.6989. Min Act: -0.1700
Data Index: 3422033 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19