Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3619 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4515. Min Range: -7.4515
Max Act: 7.4515. Min Act: -0.1700
Data Index: 467408 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4515. Min Range: -7.4515
Max Act: 7.3890. Min Act: -0.1700
Data Index: 6262651 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4515. Min Range: -7.4515
Max Act: 7.3265. Min Act: -0.1700
Data Index: 5079275 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4515. Min Range: -7.4515
Max Act: 7.2640. Min Act: -0.1700
Data Index: 8063427 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4515. Min Range: -7.4515
Max Act: 7.1702. Min Act: -0.1700
Data Index: 7194614 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4515. Min Range: -7.4515
Max Act: 7.1390. Min Act: -0.1700
Data Index: 3037105 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4515. Min Range: -7.4515
Max Act: 7.1390. Min Act: -0.1700
Data Index: 8048922 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4515. Min Range: -7.4515
Max Act: 7.0452. Min Act: -0.1700
Data Index: 1571199 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4515. Min Range: -7.4515
Max Act: 7.0140. Min Act: -0.1700
Data Index: 5393074 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4515. Min Range: -7.4515
Max Act: 6.9515. Min Act: -0.1700
Data Index: 5202523 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4515. Min Range: -7.4515
Max Act: 6.9827. Min Act: -0.1700
Data Index: 29510 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4515. Min Range: -7.4515
Max Act: 6.9202. Min Act: -0.1700
Data Index: 2526719 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4515. Min Range: -7.4515
Max Act: 6.9827. Min Act: -0.1700
Data Index: 8049946 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4515. Min Range: -7.4515
Max Act: 6.9515. Min Act: -0.1700
Data Index: 2130972 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4515. Min Range: -7.4515
Max Act: 6.9202. Min Act: -0.1700
Data Index: 6766619 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4515. Min Range: -7.4515
Max Act: 6.9202. Min Act: -0.1700
Data Index: 7409719 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4515. Min Range: -7.4515
Max Act: 6.8890. Min Act: -0.1700
Data Index: 1412183 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4515. Min Range: -7.4515
Max Act: 6.8890. Min Act: -0.1700
Data Index: 4247775 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4515. Min Range: -7.4515
Max Act: 6.8577. Min Act: -0.1700
Data Index: 7327176 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4515. Min Range: -7.4515
Max Act: 6.8577. Min Act: -0.1700
Data Index: 6504144 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19