Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4535 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1501. Min Range: -6.1501
Max Act: 6.1501. Min Act: -0.1700
Data Index: 7244854 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1501. Min Range: -6.1501
Max Act: 6.1188. Min Act: -0.1700
Data Index: 313706 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1501. Min Range: -6.1501
Max Act: 6.0563. Min Act: -0.1700
Data Index: 4627353 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1501. Min Range: -6.1501
Max Act: 6.0251. Min Act: -0.1700
Data Index: 5903282 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1501. Min Range: -6.1501
Max Act: 6.0251. Min Act: -0.1700
Data Index: 8674851 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.9313. Min Act: -0.1700
Data Index: 313702 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.9001. Min Act: -0.1700
Data Index: 543995 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.8376. Min Act: -0.1700
Data Index: 6247754 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.7751. Min Act: -0.1700
Data Index: 6263735 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.7126. Min Act: -0.1700
Data Index: 3187627 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.6813. Min Act: -0.1700
Data Index: 1912204 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.6813. Min Act: -0.1700
Data Index: 3401028 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.6188. Min Act: -0.1700
Data Index: 5903283 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.6188. Min Act: -0.1700
Data Index: 3134461 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.5563. Min Act: -0.1700
Data Index: 5605942 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.5251. Min Act: -0.1700
Data Index: 1073040 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.5251. Min Act: -0.1700
Data Index: 7654420 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.5251. Min Act: -0.1700
Data Index: 8189961 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.5251. Min Act: -0.1700
Data Index: 8754271 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1501. Min Range: -6.1501
Max Act: 5.4938. Min Act: -0.1700
Data Index: 6026720 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19