Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2059 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.7048. Min Act: -0.1700
Data Index: 7401887 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.6735. Min Act: -0.1700
Data Index: 316815 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.5173. Min Act: -0.1700
Data Index: 6760407 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4860. Min Act: -0.1700
Data Index: 1255242 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4860. Min Act: -0.1700
Data Index: 4106603 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4860. Min Act: -0.1700
Data Index: 3835938 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4548. Min Act: -0.1700
Data Index: 8444668 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4235. Min Act: -0.1700
Data Index: 8291661 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4235. Min Act: -0.1700
Data Index: 5978113 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.4235. Min Act: -0.1700
Data Index: 6374585 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3923. Min Act: -0.1700
Data Index: 5838643 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3923. Min Act: -0.1699
Data Index: 731414 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3923. Min Act: -0.1700
Data Index: 1586428 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3923. Min Act: -0.1700
Data Index: 6404438 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3610. Min Act: -0.1700
Data Index: 361561 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3610. Min Act: -0.1700
Data Index: 8639937 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3923. Min Act: -0.1700
Data Index: 1491065 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3610. Min Act: -0.1700
Data Index: 4040968 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3298. Min Act: -0.1699
Data Index: 3903621 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7048. Min Range: -5.7048
Max Act: 5.3298. Min Act: -0.1700
Data Index: 1243666 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19