Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.5665. Min Act: -0.1700
Data Index: 3538609 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.5040. Min Act: -0.1700
Data Index: 1149469 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.5040. Min Act: -0.1700
Data Index: 4709452 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.5040. Min Act: -0.1700
Data Index: 2648112 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.3790. Min Act: -0.1700
Data Index: 7134111 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.3790. Min Act: -0.1700
Data Index: 8137786 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.4415. Min Act: -0.1700
Data Index: 5984127 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.3165. Min Act: -0.1700
Data Index: 6526348 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.3165. Min Act: -0.1700
Data Index: 5828378 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.2540. Min Act: -0.1700
Data Index: 188897 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.2540. Min Act: -0.1700
Data Index: 5962891 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.2540. Min Act: -0.1700
Data Index: 5408294 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.1915. Min Act: -0.1700
Data Index: 1976395 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.1915. Min Act: -0.1700
Data Index: 4225965 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.1915. Min Act: -0.1700
Data Index: 897891 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.1915. Min Act: -0.1700
Data Index: 8288821 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.1915. Min Act: -0.1700
Data Index: 1786093 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.1915. Min Act: -0.1700
Data Index: 8607672 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.1915. Min Act: -0.1700
Data Index: 7716291 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5665. Min Range: -9.5665
Max Act: 9.1915. Min Act: -0.1700
Data Index: 8776500 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19