Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3766 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.7548. Min Act: -0.1700
Data Index: 4158035 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.6298. Min Act: -0.1700
Data Index: 5772330 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.5673. Min Act: -0.1700
Data Index: 330380 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.5673. Min Act: -0.1700
Data Index: 3820728 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.5673. Min Act: -0.1700
Data Index: 4660725 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.5673. Min Act: -0.1700
Data Index: 4339798 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.3173. Min Act: -0.1700
Data Index: 7220584 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.3798. Min Act: -0.1700
Data Index: 554867 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.2548. Min Act: -0.1700
Data Index: 4415828 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.2548. Min Act: -0.1700
Data Index: 6336311 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.2548. Min Act: -0.1700
Data Index: 308730 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.1923. Min Act: -0.1700
Data Index: 4229228 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.2548. Min Act: -0.1700
Data Index: 5721932 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.2548. Min Act: -0.1700
Data Index: 5097980 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.1923. Min Act: -0.1700
Data Index: 5794290 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.1923. Min Act: -0.1700
Data Index: 96210 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.1298. Min Act: -0.1700
Data Index: 7336322 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.1298. Min Act: -0.1700
Data Index: 7675770 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.1298. Min Act: -0.1700
Data Index: 1732565 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7548. Min Range: -8.7548
Max Act: 8.0673. Min Act: -0.1700
Data Index: 1599165 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19