Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6349 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.5134. Min Act: -0.1700
Data Index: 5087369 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.4196. Min Act: -0.1700
Data Index: 5793169 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3571. Min Act: -0.1700
Data Index: 3334717 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1696. Min Act: -0.1700
Data Index: 8392320 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1071. Min Act: -0.1700
Data Index: 1327211 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1071. Min Act: -0.1700
Data Index: 4227348 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.0446. Min Act: -0.1700
Data Index: 6455584 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.0134. Min Act: -0.1700
Data Index: 980463 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.0134. Min Act: -0.1700
Data Index: 2218312 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.9509. Min Act: -0.1700
Data Index: 1065320 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.9196. Min Act: -0.1700
Data Index: 8440991 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.9196. Min Act: -0.1700
Data Index: 8438772 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.8259. Min Act: -0.1700
Data Index: 4136908 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.7946. Min Act: -0.1700
Data Index: 4684587 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.7946. Min Act: -0.1700
Data Index: 5207658 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.7634. Min Act: -0.1700
Data Index: 2824637 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.7634. Min Act: -0.1700
Data Index: 4656654 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.7321. Min Act: -0.1700
Data Index: 8303563 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.7321. Min Act: -0.1700
Data Index: 8406401 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5134. Min Range: -5.5134
Max Act: 4.7321. Min Act: -0.1700
Data Index: 3284277 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19