Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.4807. Min Act: -0.1700
Data Index: 727000 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.4182. Min Act: -0.1700
Data Index: 2097147 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.4182. Min Act: -0.1700
Data Index: 3711671 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.4182. Min Act: -0.1700
Data Index: 4881312 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.4182. Min Act: -0.1700
Data Index: 5144469 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.4182. Min Act: -0.1700
Data Index: 214852 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.3557. Min Act: -0.1700
Data Index: 3310870 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.3557. Min Act: -0.1700
Data Index: 5794809 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.4182. Min Act: -0.1700
Data Index: 3600994 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.3557. Min Act: -0.1700
Data Index: 5500496 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.2932. Min Act: -0.1700
Data Index: 3229700 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.2932. Min Act: -0.1700
Data Index: 2137708 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.2932. Min Act: -0.1700
Data Index: 3684168 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.2307. Min Act: -0.1700
Data Index: 5794804 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.2307. Min Act: -0.1700
Data Index: 5794816 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.2307. Min Act: -0.1700
Data Index: 705678 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.1682. Min Act: -0.1699
Data Index: 660512 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.1682. Min Act: -0.1700
Data Index: 4952931 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.1682. Min Act: -0.1700
Data Index: 1034268 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4807. Min Range: -9.4807
Max Act: 9.1682. Min Act: -0.1700
Data Index: 1037562 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19