Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.6457. Min Act: -0.1700
Data Index: 5482503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.6457. Min Act: -0.1700
Data Index: 3974923 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.6145. Min Act: -0.1700
Data Index: 4249436 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.6145. Min Act: -0.1700
Data Index: 5701606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5832. Min Act: -0.1700
Data Index: 5541794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5832. Min Act: -0.1700
Data Index: 2358448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5832. Min Act: -0.1700
Data Index: 1444492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5520. Min Act: -0.1700
Data Index: 4413052 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5520. Min Act: -0.1700
Data Index: 2491235 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5520. Min Act: -0.1700
Data Index: 595451 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5207. Min Act: -0.1700
Data Index: 5529286 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4895. Min Act: -0.1700
Data Index: 2035350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4895. Min Act: -0.1700
Data Index: 5344607 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4895. Min Act: -0.1700
Data Index: 1375557 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4895. Min Act: -0.1700
Data Index: 1603616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4582. Min Act: -0.1700
Data Index: 7664142 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4582. Min Act: -0.1700
Data Index: 2065151 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4270. Min Act: -0.1700
Data Index: 5311382 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4270. Min Act: -0.1700
Data Index: 7789887 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.3957. Min Act: -0.1700
Data Index: 5639078 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19