Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.4529. Min Act: -0.1700
Data Index: 790485 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.4841. Min Act: -0.1700
Data Index: 8502675 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.4216. Min Act: -0.1700
Data Index: 2782177 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.3904. Min Act: -0.1700
Data Index: 1583040 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.2966. Min Act: -0.1700
Data Index: 8502678 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.2341. Min Act: -0.1700
Data Index: 7270814 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.2029. Min Act: -0.1700
Data Index: 2671983 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.2341. Min Act: -0.1700
Data Index: 6140371 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.2029. Min Act: -0.1700
Data Index: 881936 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.1716. Min Act: -0.1700
Data Index: 8598373 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.1404. Min Act: -0.1700
Data Index: 3778000 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.1091. Min Act: -0.1700
Data Index: 1594536 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.0779. Min Act: -0.1700
Data Index: 8749203 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.0779. Min Act: -0.1700
Data Index: 5073516 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.0466. Min Act: -0.1700
Data Index: 340360 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.0466. Min Act: -0.1700
Data Index: 3083435 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.0154. Min Act: -0.1700
Data Index: 6215786 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.0154. Min Act: -0.1700
Data Index: 749224 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4841. Min Range: -5.4841
Max Act: 5.0154. Min Act: -0.1700
Data Index: 7185154 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4841. Min Range: -5.4841
Max Act: 4.9841. Min Act: -0.1700
Data Index: 4589622 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19