Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4270 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1095. Min Range: -8.1095
Max Act: 8.1095. Min Act: -0.1700
Data Index: 8780910 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.9220. Min Act: -0.1700
Data Index: 2539353 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.7970. Min Act: -0.1700
Data Index: 8257807 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.7345. Min Act: -0.1700
Data Index: 1245987 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.7345. Min Act: -0.1700
Data Index: 5125976 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.7345. Min Act: -0.1700
Data Index: 6514026 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.6720. Min Act: -0.1700
Data Index: 4539182 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.6095. Min Act: -0.1700
Data Index: 6563916 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.6095. Min Act: -0.1700
Data Index: 1586479 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.5783. Min Act: -0.1700
Data Index: 7272093 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.5783. Min Act: -0.1700
Data Index: 6182454 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.5783. Min Act: -0.1700
Data Index: 4545008 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.5158. Min Act: -0.1700
Data Index: 8515502 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.4845. Min Act: -0.1700
Data Index: 2321809 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.4533. Min Act: -0.1700
Data Index: 4517880 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.4220. Min Act: -0.1700
Data Index: 4906350 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.4533. Min Act: -0.1700
Data Index: 4223136 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.3908. Min Act: -0.1700
Data Index: 6219612 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.3908. Min Act: -0.1700
Data Index: 1422234 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1095. Min Range: -8.1095
Max Act: 7.3595. Min Act: -0.1700
Data Index: 2656362 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19