Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4463 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.6054. Min Act: -0.1691
Data Index: 2662947 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.5663. Min Act: -0.1700
Data Index: 8451536 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.5586. Min Act: -0.1694
Data Index: 2112260 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.5355. Min Act: -0.1700
Data Index: 3732260 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.5355. Min Act: -0.1700
Data Index: 4600310 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.5279. Min Act: -0.1700
Data Index: 2065885 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.5127. Min Act: -0.1647
Data Index: 3292028 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.5203. Min Act: -0.1666
Data Index: 2279001 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.5127. Min Act: -0.1700
Data Index: 6432269 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.5127. Min Act: -0.1700
Data Index: 5876371 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.5051. Min Act: -0.1693
Data Index: 5046002 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.5051. Min Act: -0.1700
Data Index: 6541771 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.4976. Min Act: -0.1700
Data Index: 2523728 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.4976. Min Act: -0.1700
Data Index: 3073316 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.4976. Min Act: -0.1676
Data Index: 7650689 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.4901. Min Act: -0.1665
Data Index: 1481865 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.4901. Min Act: -0.1700
Data Index: 5784217 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.4827. Min Act: -0.1630
Data Index: 6337453 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.4827. Min Act: -0.1683
Data Index: 3449725 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6054. Min Range: -0.6054
Max Act: 0.4827. Min Act: -0.1694
Data Index: 4263989 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19