Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5678 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.6266. Min Act: -0.1700
Data Index: 5432572 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.6109. Min Act: -0.1700
Data Index: 2304826 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.5796. Min Act: -0.1700
Data Index: 1732884 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.5483. Min Act: -0.1700
Data Index: 7486783 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.5483. Min Act: -0.1700
Data Index: 866677 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.5483. Min Act: -0.1700
Data Index: 5308169 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.5170. Min Act: -0.1700
Data Index: 1961160 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.5013. Min Act: -0.1700
Data Index: 2506313 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.5013. Min Act: -0.1700
Data Index: 739795 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.5013. Min Act: -0.1700
Data Index: 4017359 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.5013. Min Act: -0.1700
Data Index: 2290544 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.4700. Min Act: -0.1700
Data Index: 2935991 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.4700. Min Act: -0.1700
Data Index: 8262997 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.4700. Min Act: -0.1700
Data Index: 4996606 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.4387. Min Act: -0.1700
Data Index: 7894099 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.4544. Min Act: -0.1700
Data Index: 50664 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.4544. Min Act: -0.1700
Data Index: 4697403 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.4544. Min Act: -0.1700
Data Index: 7205633 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.4387. Min Act: -0.1700
Data Index: 7727504 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6266. Min Range: -3.6266
Max Act: 3.4387. Min Act: -0.1700
Data Index: 3199873 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19