Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.6472. Min Act: -0.1700
Data Index: 340881 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.6160. Min Act: -0.1700
Data Index: 1402740 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.3659. Min Act: -0.1700
Data Index: 2306992 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.3659. Min Act: -0.1700
Data Index: 1402737 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.2722. Min Act: -0.1700
Data Index: 168076 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.2722. Min Act: -0.1700
Data Index: 8147303 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.2409. Min Act: -0.1700
Data Index: 1653520 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.2409. Min Act: -0.1700
Data Index: 4275918 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.1784. Min Act: -0.1700
Data Index: 4478993 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.1784. Min Act: -0.1700
Data Index: 8559726 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.1784. Min Act: -0.1700
Data Index: 7971823 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.1159. Min Act: -0.1700
Data Index: 1677440 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.1472. Min Act: -0.1700
Data Index: 168074 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.1159. Min Act: -0.1700
Data Index: 3063445 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.1159. Min Act: -0.1700
Data Index: 3029060 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.1159. Min Act: -0.1700
Data Index: 4462598 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.1159. Min Act: -0.1700
Data Index: 6785417 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.0847. Min Act: -0.1700
Data Index: 722273 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.0847. Min Act: -0.1700
Data Index: 2898258 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6472. Min Range: -4.6472
Max Act: 4.0847. Min Act: -0.1700
Data Index: 6442570 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19