Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.8158. Min Act: -0.1700
Data Index: 3081981 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.8158. Min Act: -0.1700
Data Index: 1517202 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.8158. Min Act: -0.1700
Data Index: 7557252 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.7845. Min Act: -0.1700
Data Index: 6296471 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.7533. Min Act: -0.1700
Data Index: 3081978 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.7220. Min Act: -0.1700
Data Index: 3081986 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.7220. Min Act: -0.1700
Data Index: 7450725 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.6908. Min Act: -0.1700
Data Index: 3081972 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.6908. Min Act: -0.1700
Data Index: 2913775 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.6595. Min Act: -0.1700
Data Index: 3676275 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.6595. Min Act: -0.1700
Data Index: 828635 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.6595. Min Act: -0.1700
Data Index: 3081985 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.6283. Min Act: -0.1700
Data Index: 3081982 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.6283. Min Act: -0.1700
Data Index: 3081973 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.5658. Min Act: -0.1700
Data Index: 7557248 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.5970. Min Act: -0.1700
Data Index: 3081995 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.5658. Min Act: -0.1700
Data Index: 8137252 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.5033. Min Act: -0.1700
Data Index: 7557250 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.5033. Min Act: -0.1700
Data Index: 828636 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8158. Min Range: -4.8158
Max Act: 4.4720. Min Act: -0.1700
Data Index: 3081977 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19