Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 716 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.9263. Min Act: -0.1700
Data Index: 3251585 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.8951. Min Act: -0.1700
Data Index: 1840418 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.8638. Min Act: -0.1700
Data Index: 1371047 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.8638. Min Act: -0.1700
Data Index: 3493642 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.8326. Min Act: -0.1700
Data Index: 5410001 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.8013. Min Act: -0.1700
Data Index: 6926623 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.7701. Min Act: -0.1700
Data Index: 8577663 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.7701. Min Act: -0.1700
Data Index: 5268194 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.7076. Min Act: -0.1700
Data Index: 4495873 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6763. Min Act: -0.1700
Data Index: 544372 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6451. Min Act: -0.1700
Data Index: 6974431 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6451. Min Act: -0.1700
Data Index: 7291578 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6451. Min Act: -0.1700
Data Index: 6284136 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6451. Min Act: -0.1700
Data Index: 2802693 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6451. Min Act: -0.1700
Data Index: 8581447 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6763. Min Act: -0.1700
Data Index: 6531604 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6138. Min Act: -0.1700
Data Index: 6028070 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6138. Min Act: -0.1700
Data Index: 8186973 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6138. Min Act: -0.1700
Data Index: 5845471 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6451. Min Act: -0.1700
Data Index: 2363190 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19