Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2114 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.6094. Min Act: -0.1680
Data Index: 4258711 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.6094. Min Act: -0.1663
Data Index: 2004910 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.6094. Min Act: -0.1700
Data Index: 7827074 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.6094. Min Act: -0.1700
Data Index: 6304307 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5919. Min Act: -0.1333
Data Index: 7083128 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5919. Min Act: -0.1656
Data Index: 1168520 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5832. Min Act: -0.1445
Data Index: 2590256 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5744. Min Act: -0.1692
Data Index: 4516216 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5657. Min Act: -0.1700
Data Index: 7004263 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5657. Min Act: -0.1700
Data Index: 5149218 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5657. Min Act: -0.1700
Data Index: 1969342 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5569. Min Act: -0.1481
Data Index: 7438481 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5569. Min Act: -0.1407
Data Index: 1021464 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5569. Min Act: -0.1700
Data Index: 713052 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5482. Min Act: -0.1700
Data Index: 2038788 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5482. Min Act: -0.1700
Data Index: 6812547 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5482. Min Act: -0.1599
Data Index: 2590268 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5482. Min Act: -0.1653
Data Index: 2004908 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5394. Min Act: -0.1700
Data Index: 1568403 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6094. Min Range: -1.6094
Max Act: 1.5482. Min Act: -0.1274
Data Index: 5149217 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19