Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.8781. Min Act: -0.1700
Data Index: 4746060 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.6594. Min Act: -0.1700
Data Index: 712689 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.6594. Min Act: -0.1700
Data Index: 3935736 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.6594. Min Act: -0.1700
Data Index: 2864886 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.5344. Min Act: -0.1700
Data Index: 3515085 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.5656. Min Act: -0.1700
Data Index: 689681 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.5031. Min Act: -0.1700
Data Index: 4476565 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4719. Min Act: -0.1700
Data Index: 3158514 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4719. Min Act: -0.1700
Data Index: 7262790 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4719. Min Act: -0.1700
Data Index: 599532 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4406. Min Act: -0.1700
Data Index: 5996215 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4406. Min Act: -0.1700
Data Index: 1941177 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4719. Min Act: -0.1700
Data Index: 8313022 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4406. Min Act: -0.1700
Data Index: 5445909 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4406. Min Act: -0.1700
Data Index: 827656 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4094. Min Act: -0.1700
Data Index: 8651725 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4094. Min Act: -0.1700
Data Index: 7502700 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4094. Min Act: -0.1700
Data Index: 8123163 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4406. Min Act: -0.1700
Data Index: 5041010 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.3781. Min Act: -0.1700
Data Index: 3007576 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19