Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.9349. Min Act: -0.1700
Data Index: 5222097 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.6537. Min Act: -0.1700
Data Index: 6879624 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.6224. Min Act: -0.1700
Data Index: 6271762 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.4974. Min Act: -0.1700
Data Index: 1245155 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.4349. Min Act: -0.1700
Data Index: 6624701 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.4037. Min Act: -0.1700
Data Index: 4950376 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.4037. Min Act: -0.1700
Data Index: 7835774 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.3412. Min Act: -0.1700
Data Index: 8222320 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.3412. Min Act: -0.1700
Data Index: 7216810 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.3099. Min Act: -0.1700
Data Index: 5100681 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.3099. Min Act: -0.1700
Data Index: 268777 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.3412. Min Act: -0.1700
Data Index: 4336647 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.3412. Min Act: -0.1700
Data Index: 4758948 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.2787. Min Act: -0.1700
Data Index: 557737 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.2787. Min Act: -0.1700
Data Index: 7518308 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.2787. Min Act: -0.1700
Data Index: 5711669 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.2474. Min Act: -0.1700
Data Index: 2019954 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.2162. Min Act: -0.1700
Data Index: 6479567 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.2474. Min Act: -0.1700
Data Index: 745420 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9349. Min Range: -7.9349
Max Act: 7.2474. Min Act: -0.1700
Data Index: 4824255 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19