Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0900. Min Range: -6.0900
Max Act: 6.0900. Min Act: -0.1700
Data Index: 1218767 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0900. Min Range: -6.0900
Max Act: 6.0900. Min Act: -0.1700
Data Index: 3719478 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9962. Min Act: -0.1700
Data Index: 5872478 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9962. Min Act: -0.1700
Data Index: 3342243 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9962. Min Act: -0.1700
Data Index: 107084 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9962. Min Act: -0.1700
Data Index: 8257440 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9650. Min Act: -0.1700
Data Index: 4565419 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9650. Min Act: -0.1700
Data Index: 7077935 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9650. Min Act: -0.1700
Data Index: 3593007 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9650. Min Act: -0.1700
Data Index: 4669146 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9650. Min Act: -0.1700
Data Index: 8484120 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9337. Min Act: -0.1700
Data Index: 6783803 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9650. Min Act: -0.1700
Data Index: 683096 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9337. Min Act: -0.1696
Data Index: 6989033 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9025. Min Act: -0.1700
Data Index: 5640924 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9025. Min Act: -0.1697
Data Index: 8469334 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.8712. Min Act: -0.1700
Data Index: 767359 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.8400. Min Act: -0.1700
Data Index: 2130697 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.8712. Min Act: -0.1700
Data Index: 4614595 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0900. Min Range: -6.0900
Max Act: 5.9025. Min Act: -0.1700
Data Index: 6982888 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19