Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 887 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0536. Min Range: -8.0536
Max Act: 8.0536. Min Act: -0.1700
Data Index: 3031888 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.9911. Min Act: -0.1700
Data Index: 1774106 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.9911. Min Act: -0.1700
Data Index: 7192976 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.8661. Min Act: -0.1700
Data Index: 1860536 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.8661. Min Act: -0.1700
Data Index: 1274149 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.8036. Min Act: -0.1700
Data Index: 4424864 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.6786. Min Act: -0.1700
Data Index: 2727303 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.6161. Min Act: -0.1700
Data Index: 8606612 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.6161. Min Act: -0.1700
Data Index: 8242209 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.5223. Min Act: -0.1700
Data Index: 5752633 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.5848. Min Act: -0.1700
Data Index: 1376312 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.5223. Min Act: -0.1700
Data Index: 898942 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.4911. Min Act: -0.1700
Data Index: 4542574 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.4286. Min Act: -0.1700
Data Index: 5897147 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.4286. Min Act: -0.1700
Data Index: 213422 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.4286. Min Act: -0.1700
Data Index: 4539144 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.4286. Min Act: -0.1700
Data Index: 2093082 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.3973. Min Act: -0.1700
Data Index: 216576 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.3661. Min Act: -0.1700
Data Index: 5380394 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.3973. Min Act: -0.1700
Data Index: 3327588 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19