Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5422 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5772. Min Act: -0.1700
Data Index: 372205 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5772. Min Act: -0.1700
Data Index: 4207446 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5772. Min Act: -0.1700
Data Index: 7404765 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5772. Min Act: -0.1700
Data Index: 5861334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5460. Min Act: -0.1700
Data Index: 188770 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5460. Min Act: -0.1700
Data Index: 4426776 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5147. Min Act: -0.1700
Data Index: 1788137 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5147. Min Act: -0.1700
Data Index: 3582990 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5460. Min Act: -0.1700
Data Index: 5550084 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5147. Min Act: -0.1700
Data Index: 3305138 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5147. Min Act: -0.1700
Data Index: 3275219 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.4835. Min Act: -0.1700
Data Index: 4782964 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5147. Min Act: -0.1700
Data Index: 8239545 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.4835. Min Act: -0.1700
Data Index: 5593724 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.4835. Min Act: -0.1700
Data Index: 1447265 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.4835. Min Act: -0.1700
Data Index: 1699919 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.4835. Min Act: -0.1700
Data Index: 5823730 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.4522. Min Act: -0.1700
Data Index: 5508626 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.4835. Min Act: -0.1700
Data Index: 6337207 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.4835. Min Act: -0.1700
Data Index: 6978037 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19