Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.6997. Min Act: -0.1700
Data Index: 4128239 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.5122. Min Act: -0.1700
Data Index: 4769540 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.4497. Min Act: -0.1700
Data Index: 2345070 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.3872. Min Act: -0.1700
Data Index: 1086500 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.3872. Min Act: -0.1700
Data Index: 2830626 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.3560. Min Act: -0.1700
Data Index: 4641667 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.3872. Min Act: -0.1700
Data Index: 4925297 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.4185. Min Act: -0.1700
Data Index: 6292163 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.3560. Min Act: -0.1700
Data Index: 1533904 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.3560. Min Act: -0.1700
Data Index: 8115114 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.3247. Min Act: -0.1700
Data Index: 7868837 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.2934. Min Act: -0.1700
Data Index: 832359 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.2934. Min Act: -0.1700
Data Index: 3773055 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.2934. Min Act: -0.1700
Data Index: 4925296 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.2309. Min Act: -0.1700
Data Index: 8337239 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.2622. Min Act: -0.1700
Data Index: 4041633 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.2309. Min Act: -0.1700
Data Index: 5267830 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.2309. Min Act: -0.1700
Data Index: 5210299 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.2309. Min Act: -0.1700
Data Index: 7130743 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6997. Min Range: -4.6997
Max Act: 4.2309. Min Act: -0.1700
Data Index: 3459367 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19