Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 691 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2273. Min Range: -6.2273
Max Act: 6.1961. Min Act: -0.1700
Data Index: 5650083 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2273. Min Range: -6.2273
Max Act: 6.2273. Min Act: -0.1700
Data Index: 3352252 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2273. Min Range: -6.2273
Max Act: 6.1648. Min Act: -0.1700
Data Index: 1918522 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2273. Min Range: -6.2273
Max Act: 6.1023. Min Act: -0.1700
Data Index: 5545101 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2273. Min Range: -6.2273
Max Act: 6.0398. Min Act: -0.1700
Data Index: 1559555 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2273. Min Range: -6.2273
Max Act: 6.0086. Min Act: -0.1700
Data Index: 8093068 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.9773. Min Act: -0.1700
Data Index: 4765203 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.9461. Min Act: -0.1700
Data Index: 2112852 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.8836. Min Act: -0.1700
Data Index: 4709974 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.8836. Min Act: -0.1700
Data Index: 6426861 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.8211. Min Act: -0.1700
Data Index: 3859345 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.8523. Min Act: -0.1700
Data Index: 2335887 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.8211. Min Act: -0.1700
Data Index: 3761843 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.7586. Min Act: -0.1700
Data Index: 4108517 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.7273. Min Act: -0.1700
Data Index: 5133453 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.7273. Min Act: -0.1700
Data Index: 6986003 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.7273. Min Act: -0.1700
Data Index: 4327969 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.7586. Min Act: -0.1700
Data Index: 7130376 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.7273. Min Act: -0.1700
Data Index: 6907384 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2273. Min Range: -6.2273
Max Act: 5.7273. Min Act: -0.1700
Data Index: 2624274 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19