Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4068 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7672. Min Range: -10.7672
Max Act: 10.7672. Min Act: -0.1700
Data Index: 6010169 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7672. Min Range: -10.7672
Max Act: 10.5172. Min Act: -0.1700
Data Index: 4640267 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7672. Min Range: -10.7672
Max Act: 10.1422. Min Act: -0.1700
Data Index: 6139228 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7672. Min Range: -10.7672
Max Act: 10.1422. Min Act: -0.1700
Data Index: 617225 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.8297. Min Act: -0.1700
Data Index: 2639532 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.8297. Min Act: -0.1700
Data Index: 300685 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.7672. Min Act: -0.1700
Data Index: 1611264 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.7672. Min Act: -0.1700
Data Index: 7663194 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.7047. Min Act: -0.1700
Data Index: 6032522 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.7047. Min Act: -0.1700
Data Index: 8120803 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.6422. Min Act: -0.1700
Data Index: 7681815 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.6422. Min Act: -0.1700
Data Index: 2871692 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.6422. Min Act: -0.1700
Data Index: 4768043 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.5172. Min Act: -0.1700
Data Index: 463002 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.5172. Min Act: -0.1700
Data Index: 5545916 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.5797. Min Act: -0.1700
Data Index: 818079 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.5172. Min Act: -0.1700
Data Index: 1073882 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.5797. Min Act: -0.1700
Data Index: 3791373 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.5172. Min Act: -0.1700
Data Index: 3012576 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7672. Min Range: -10.7672
Max Act: 9.5172. Min Act: -0.1700
Data Index: 1518311 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19