Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 398 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.8783. Min Act: -0.1700
Data Index: 8604862 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.7533. Min Act: -0.1700
Data Index: 7215054 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.5658. Min Act: -0.1700
Data Index: 2049280 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.3783. Min Act: -0.1700
Data Index: 6057998 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.3158. Min Act: -0.1700
Data Index: 3325918 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.3158. Min Act: -0.1700
Data Index: 1208298 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.2533. Min Act: -0.1700
Data Index: 1393887 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.1908. Min Act: -0.1700
Data Index: 6566466 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.1908. Min Act: -0.1700
Data Index: 4862074 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.1908. Min Act: -0.1700
Data Index: 1087211 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.0658. Min Act: -0.1700
Data Index: 7353175 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.0033. Min Act: -0.1700
Data Index: 5837641 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8783. Min Range: -10.8783
Max Act: 10.0033. Min Act: -0.1700
Data Index: 5432508 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8783. Min Range: -10.8783
Max Act: 9.9408. Min Act: -0.1700
Data Index: 4265116 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8783. Min Range: -10.8783
Max Act: 9.9408. Min Act: -0.1700
Data Index: 6356435 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8783. Min Range: -10.8783
Max Act: 9.8158. Min Act: -0.1700
Data Index: 3120670 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8783. Min Range: -10.8783
Max Act: 9.8783. Min Act: -0.1700
Data Index: 7442619 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8783. Min Range: -10.8783
Max Act: 9.8783. Min Act: -0.1700
Data Index: 7528304 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8783. Min Range: -10.8783
Max Act: 9.8783. Min Act: -0.1700
Data Index: 7554665 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8783. Min Range: -10.8783
Max Act: 9.8783. Min Act: -0.1700
Data Index: 5150990 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19