Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5279 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0036. Min Range: -5.0036
Max Act: 5.0036. Min Act: -0.1700
Data Index: 7130198 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.7224. Min Act: -0.1700
Data Index: 5417753 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.7224. Min Act: -0.1700
Data Index: 658867 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.7224. Min Act: -0.1700
Data Index: 7181548 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.7224. Min Act: -0.1700
Data Index: 8048120 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.6286. Min Act: -0.1700
Data Index: 3765088 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.6599. Min Act: -0.1700
Data Index: 7284952 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.6599. Min Act: -0.1700
Data Index: 6911454 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.6286. Min Act: -0.1700
Data Index: 1733389 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.6286. Min Act: -0.1700
Data Index: 1670812 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.6286. Min Act: -0.1700
Data Index: 3368148 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.6286. Min Act: -0.1700
Data Index: 8035304 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.5974. Min Act: -0.1700
Data Index: 3516744 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.5974. Min Act: -0.1700
Data Index: 894312 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.5974. Min Act: -0.1700
Data Index: 1828433 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.5661. Min Act: -0.1700
Data Index: 377820 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.5661. Min Act: -0.1700
Data Index: 5479403 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.5661. Min Act: -0.1700
Data Index: 398795 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.5661. Min Act: -0.1700
Data Index: 5460674 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0036. Min Range: -5.0036
Max Act: 4.5349. Min Act: -0.1700
Data Index: 1628866 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19