Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5365 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.7736. Min Act: -0.1700
Data Index: 7029149 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.4611. Min Act: -0.1700
Data Index: 4239619 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.4611. Min Act: -0.1700
Data Index: 86488 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.4299. Min Act: -0.1700
Data Index: 5121563 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.3674. Min Act: -0.1700
Data Index: 8729570 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.3361. Min Act: -0.1700
Data Index: 5442162 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.3361. Min Act: -0.1700
Data Index: 8546012 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.2736. Min Act: -0.1700
Data Index: 8210396 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.2736. Min Act: -0.1700
Data Index: 3255775 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.2424. Min Act: -0.1700
Data Index: 1559030 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.2111. Min Act: -0.1700
Data Index: 8822323 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.2111. Min Act: -0.1700
Data Index: 3081057 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.1799. Min Act: -0.1700
Data Index: 342730 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.1799. Min Act: -0.1700
Data Index: 3593474 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.1799. Min Act: -0.1700
Data Index: 383609 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.1486. Min Act: -0.1700
Data Index: 3050269 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.1174. Min Act: -0.1700
Data Index: 5533054 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.1174. Min Act: -0.1700
Data Index: 7207599 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.1174. Min Act: -0.1700
Data Index: 1625116 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7736. Min Range: -6.7736
Max Act: 6.0861. Min Act: -0.1700
Data Index: 7989482 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19