Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2464 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5729. Min Act: -0.1700
Data Index: 1836316 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5729. Min Act: -0.1700
Data Index: 8371835 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5729. Min Act: -0.1700
Data Index: 6790942 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5416. Min Act: -0.1700
Data Index: 6420408 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5416. Min Act: -0.1700
Data Index: 8463298 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5416. Min Act: -0.1700
Data Index: 8120221 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5416. Min Act: -0.1700
Data Index: 2225685 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5416. Min Act: -0.1700
Data Index: 6521123 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 7540468 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 4255853 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 3940574 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 2703055 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 8086606 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 26303 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 6441982 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 3860219 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 3337693 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 1544028 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.4790. Min Act: -0.1700
Data Index: 2482380 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.4790. Min Act: -0.1700
Data Index: 2951670 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19