Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2611 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.3645. Min Act: -0.1700
Data Index: 4812636 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.2395. Min Act: -0.1700
Data Index: 5724650 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.2083. Min Act: -0.1700
Data Index: 634466 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.2395. Min Act: -0.1700
Data Index: 4865804 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.1458. Min Act: -0.1700
Data Index: 2799115 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.1458. Min Act: -0.1700
Data Index: 1000934 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.1458. Min Act: -0.1700
Data Index: 134122 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.1458. Min Act: -0.1700
Data Index: 5600618 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.1145. Min Act: -0.1700
Data Index: 4148554 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.1145. Min Act: -0.1700
Data Index: 1279204 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0833. Min Act: -0.1700
Data Index: 1682870 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0833. Min Act: -0.1700
Data Index: 3885477 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0833. Min Act: -0.1700
Data Index: 8593429 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0833. Min Act: -0.1700
Data Index: 6886006 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 5960373 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 109722 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 4128398 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 3473019 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0208. Min Act: -0.1700
Data Index: 5702190 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3645. Min Range: -5.3645
Max Act: 5.0520. Min Act: -0.1700
Data Index: 3090365 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19