Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2350 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0047. Min Range: -6.0047
Max Act: 6.0047. Min Act: -0.1700
Data Index: 3998684 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0047. Min Range: -6.0047
Max Act: 6.0047. Min Act: -0.1700
Data Index: 6162214 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.8484. Min Act: -0.1700
Data Index: 3775206 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.7234. Min Act: -0.1700
Data Index: 4240419 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.7547. Min Act: -0.1700
Data Index: 3369032 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.7234. Min Act: -0.1700
Data Index: 4817816 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.7234. Min Act: -0.1700
Data Index: 606671 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.6609. Min Act: -0.1700
Data Index: 5479768 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.6609. Min Act: -0.1700
Data Index: 2312701 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.6609. Min Act: -0.1700
Data Index: 3531804 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.6609. Min Act: -0.1700
Data Index: 881921 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.5984. Min Act: -0.1700
Data Index: 2924651 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.5984. Min Act: -0.1700
Data Index: 7945315 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.5984. Min Act: -0.1700
Data Index: 4449360 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.5672. Min Act: -0.1700
Data Index: 1522802 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.5359. Min Act: -0.1700
Data Index: 3009008 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.5672. Min Act: -0.1700
Data Index: 5606150 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.5047. Min Act: -0.1700
Data Index: 5221724 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.5047. Min Act: -0.1700
Data Index: 6656495 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0047. Min Range: -6.0047
Max Act: 5.4734. Min Act: -0.1700
Data Index: 689920 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19