Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.7354. Min Act: -0.1700
Data Index: 7458181 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.7041. Min Act: -0.1700
Data Index: 382728 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.6729. Min Act: -0.1700
Data Index: 2482414 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.6104. Min Act: -0.1700
Data Index: 5008578 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.6416. Min Act: -0.1700
Data Index: 1003568 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.6416. Min Act: -0.1700
Data Index: 2482413 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.5479. Min Act: -0.1700
Data Index: 2021600 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.5166. Min Act: -0.1700
Data Index: 7618617 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.5166. Min Act: -0.1700
Data Index: 8590877 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4854. Min Act: -0.1700
Data Index: 1745491 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4541. Min Act: -0.1700
Data Index: 4372271 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4541. Min Act: -0.1700
Data Index: 7914264 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4229. Min Act: -0.1700
Data Index: 3739924 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.3916. Min Act: -0.1700
Data Index: 975001 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.3916. Min Act: -0.1700
Data Index: 40792 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.3604. Min Act: -0.1700
Data Index: 7618615 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.3604. Min Act: -0.1700
Data Index: 6550913 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.3604. Min Act: -0.1700
Data Index: 6983239 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.3291. Min Act: -0.1700
Data Index: 2873916 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.2979. Min Act: -0.1700
Data Index: 810720 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19