Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2260 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0440. Min Range: -6.0440
Max Act: 6.0440. Min Act: -0.1700
Data Index: 4082122 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0440. Min Range: -6.0440
Max Act: 6.0440. Min Act: -0.1700
Data Index: 4016810 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.8878. Min Act: -0.1700
Data Index: 1280975 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.8878. Min Act: -0.1700
Data Index: 6554454 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.8253. Min Act: -0.1700
Data Index: 897917 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.7315. Min Act: -0.1700
Data Index: 1698584 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.7628. Min Act: -0.1700
Data Index: 1892053 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.7315. Min Act: -0.1700
Data Index: 1105159 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.6690. Min Act: -0.1700
Data Index: 7862238 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.6690. Min Act: -0.1700
Data Index: 5836207 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.6065. Min Act: -0.1700
Data Index: 7593758 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.6378. Min Act: -0.1700
Data Index: 353392 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.6065. Min Act: -0.1700
Data Index: 5490584 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.6065. Min Act: -0.1700
Data Index: 4635168 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.6065. Min Act: -0.1700
Data Index: 8204012 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.6065. Min Act: -0.1700
Data Index: 210038 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.6065. Min Act: -0.1700
Data Index: 4529573 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.5753. Min Act: -0.1700
Data Index: 8002245 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.5753. Min Act: -0.1700
Data Index: 6258908 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.5753. Min Act: -0.1700
Data Index: 2362638 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19