Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1602. Min Range: -6.1602
Max Act: 6.1602. Min Act: -0.1700
Data Index: 1799578 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1602. Min Range: -6.1602
Max Act: 6.0664. Min Act: -0.1700
Data Index: 5761986 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1602. Min Range: -6.1602
Max Act: 6.0664. Min Act: -0.1700
Data Index: 4518375 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1602. Min Range: -6.1602
Max Act: 6.0352. Min Act: -0.1700
Data Index: 5633472 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1602. Min Range: -6.1602
Max Act: 6.0352. Min Act: -0.1700
Data Index: 1848459 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.9727. Min Act: -0.1700
Data Index: 2471777 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.9727. Min Act: -0.1700
Data Index: 7568416 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.9414. Min Act: -0.1700
Data Index: 7019406 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.9414. Min Act: -0.1700
Data Index: 6007237 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.9102. Min Act: -0.1700
Data Index: 5994935 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.9102. Min Act: -0.1700
Data Index: 8427222 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.9102. Min Act: -0.1700
Data Index: 7167410 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.9102. Min Act: -0.1700
Data Index: 8799880 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.8789. Min Act: -0.1700
Data Index: 5374148 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.8789. Min Act: -0.1700
Data Index: 1659941 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.8477. Min Act: -0.1700
Data Index: 6275817 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.8477. Min Act: -0.1700
Data Index: 7612800 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.8477. Min Act: -0.1700
Data Index: 1236632 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.8164. Min Act: -0.1700
Data Index: 7469023 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1602. Min Range: -6.1602
Max Act: 5.8164. Min Act: -0.1700
Data Index: 1177147 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19