Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 471 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1169. Min Range: -3.1169
Max Act: 3.1169. Min Act: -0.1700
Data Index: 8670407 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1169. Min Range: -3.1169
Max Act: 3.1012. Min Act: -0.1700
Data Index: 8776746 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1169. Min Range: -3.1169
Max Act: 3.0381. Min Act: -0.1700
Data Index: 8170486 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1169. Min Range: -3.1169
Max Act: 3.0065. Min Act: -0.1700
Data Index: 8226755 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.9591. Min Act: -0.1700
Data Index: 5663213 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.8322. Min Act: -0.1700
Data Index: 5215308 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.8163. Min Act: -0.1700
Data Index: 6663288 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.8163. Min Act: -0.1700
Data Index: 6950322 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.8163. Min Act: -0.1700
Data Index: 7013482 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.8003. Min Act: -0.1700
Data Index: 3723776 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.8322. Min Act: -0.1700
Data Index: 2417024 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.8003. Min Act: -0.1700
Data Index: 6414381 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.8003. Min Act: -0.1700
Data Index: 4825171 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.7844. Min Act: -0.1700
Data Index: 7872155 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.7844. Min Act: -0.1700
Data Index: 360115 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.7685. Min Act: -0.1700
Data Index: 3880235 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.7525. Min Act: -0.1700
Data Index: 1245252 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.7366. Min Act: -0.1700
Data Index: 125408 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.7366. Min Act: -0.1700
Data Index: 1469521 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1169. Min Range: -3.1169
Max Act: 2.7046. Min Act: -0.1700
Data Index: 5270450 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19