Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4109 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.3676. Min Act: -0.1700
Data Index: 3029660 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.3363. Min Act: -0.1700
Data Index: 1729341 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.3363. Min Act: -0.1700
Data Index: 2183618 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.3363. Min Act: -0.1700
Data Index: 3040940 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.2113. Min Act: -0.1700
Data Index: 1934099 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.1488. Min Act: -0.1700
Data Index: 5853544 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.1801. Min Act: -0.1700
Data Index: 4718742 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.1801. Min Act: -0.1700
Data Index: 1740828 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.1801. Min Act: -0.1700
Data Index: 4312232 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.2113. Min Act: -0.1700
Data Index: 2484864 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.1488. Min Act: -0.1699
Data Index: 7590452 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.1176. Min Act: -0.1700
Data Index: 3785244 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.1176. Min Act: -0.1700
Data Index: 4412671 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.1488. Min Act: -0.1700
Data Index: 1511841 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.1176. Min Act: -0.1700
Data Index: 8551163 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.1176. Min Act: -0.1700
Data Index: 8137234 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.0863. Min Act: -0.1700
Data Index: 6819785 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.0863. Min Act: -0.1700
Data Index: 4627206 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.0551. Min Act: -0.1700
Data Index: 7443827 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3676. Min Range: -6.3676
Max Act: 6.0863. Min Act: -0.1699
Data Index: 2614998 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19