Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.5405. Min Act: -0.1700
Data Index: 3165337 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.3842. Min Act: -0.1700
Data Index: 8625531 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.3530. Min Act: -0.1700
Data Index: 3883470 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1967. Min Act: -0.1700
Data Index: 5293938 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1967. Min Act: -0.1700
Data Index: 6117549 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1655. Min Act: -0.1700
Data Index: 7348119 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1655. Min Act: -0.1700
Data Index: 792483 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1967. Min Act: -0.1700
Data Index: 852936 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1967. Min Act: -0.1700
Data Index: 5102190 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1342. Min Act: -0.1700
Data Index: 887380 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1655. Min Act: -0.1700
Data Index: 7180273 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1655. Min Act: -0.1700
Data Index: 1203931 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1655. Min Act: -0.1700
Data Index: 7405613 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1342. Min Act: -0.1700
Data Index: 2075579 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1342. Min Act: -0.1700
Data Index: 8638139 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1342. Min Act: -0.1700
Data Index: 7679725 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1342. Min Act: -0.1700
Data Index: 7576175 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1655. Min Act: -0.1700
Data Index: 4231185 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1655. Min Act: -0.1700
Data Index: 1130686 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5405. Min Range: -4.5405
Max Act: 4.1030. Min Act: -0.1700
Data Index: 6900163 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19