Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2949 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3634. Min Range: -8.3634
Max Act: 8.3634. Min Act: -0.1700
Data Index: 966198 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3634. Min Range: -8.3634
Max Act: 8.2071. Min Act: -0.1700
Data Index: 8168084 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3634. Min Range: -8.3634
Max Act: 8.1759. Min Act: -0.1700
Data Index: 4131208 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3634. Min Range: -8.3634
Max Act: 8.0509. Min Act: -0.1700
Data Index: 3515118 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.8634. Min Act: -0.1700
Data Index: 1704294 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.8009. Min Act: -0.1700
Data Index: 1058262 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.8634. Min Act: -0.1700
Data Index: 4719617 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.7696. Min Act: -0.1700
Data Index: 4764752 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.7696. Min Act: -0.1700
Data Index: 6546088 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.7071. Min Act: -0.1700
Data Index: 1077357 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.7071. Min Act: -0.1700
Data Index: 4780870 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.7071. Min Act: -0.1700
Data Index: 7642812 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.6759. Min Act: -0.1700
Data Index: 5748271 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.6759. Min Act: -0.1700
Data Index: 7389054 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.6446. Min Act: -0.1700
Data Index: 6257439 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.5821. Min Act: -0.1700
Data Index: 8376537 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.5821. Min Act: -0.1700
Data Index: 2510952 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.6446. Min Act: -0.1700
Data Index: 7189160 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.5509. Min Act: -0.1700
Data Index: 1833704 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3634. Min Range: -8.3634
Max Act: 7.5509. Min Act: -0.1700
Data Index: 5777562 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19