Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2021. Min Range: -5.2021
Max Act: 5.2021. Min Act: -0.1700
Data Index: 2287709 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2021. Min Range: -5.2021
Max Act: 5.1396. Min Act: -0.1700
Data Index: 8421113 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2021. Min Range: -5.2021
Max Act: 5.0146. Min Act: -0.1700
Data Index: 3154066 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2021. Min Range: -5.2021
Max Act: 5.0146. Min Act: -0.1700
Data Index: 4517438 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2021. Min Range: -5.2021
Max Act: 5.0146. Min Act: -0.1700
Data Index: 2385245 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.9834. Min Act: -0.1700
Data Index: 1104147 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.9209. Min Act: -0.1700
Data Index: 5880675 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.9209. Min Act: -0.1700
Data Index: 5685429 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.8896. Min Act: -0.1700
Data Index: 8263475 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.8896. Min Act: -0.1700
Data Index: 5184537 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.9209. Min Act: -0.1700
Data Index: 67227 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.8896. Min Act: -0.1700
Data Index: 8305124 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.8896. Min Act: -0.1700
Data Index: 8314507 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.8896. Min Act: -0.1700
Data Index: 1490284 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.8896. Min Act: -0.1700
Data Index: 4158680 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.8584. Min Act: -0.1700
Data Index: 1554512 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.8584. Min Act: -0.1700
Data Index: 4135103 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.8584. Min Act: -0.1700
Data Index: 6430073 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.8896. Min Act: -0.1700
Data Index: 1408935 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2021. Min Range: -5.2021
Max Act: 4.8584. Min Act: -0.1700
Data Index: 7444000 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19