Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 974 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0850. Min Range: -5.0850
Max Act: 5.0850. Min Act: -0.1700
Data Index: 1542739 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.7725. Min Act: -0.1700
Data Index: 796809 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.7100. Min Act: -0.1700
Data Index: 294671 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.6788. Min Act: -0.1700
Data Index: 778061 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.6163. Min Act: -0.1700
Data Index: 972639 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.5538. Min Act: -0.1700
Data Index: 4997144 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.5225. Min Act: -0.1700
Data Index: 3379011 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.5225. Min Act: -0.1700
Data Index: 5694690 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.5225. Min Act: -0.1700
Data Index: 7643516 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.5225. Min Act: -0.1700
Data Index: 2736382 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.4913. Min Act: -0.1700
Data Index: 8171 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.4913. Min Act: -0.1700
Data Index: 8592085 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.4288. Min Act: -0.1700
Data Index: 4895190 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.4600. Min Act: -0.1700
Data Index: 6835221 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.4600. Min Act: -0.1700
Data Index: 2271969 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.4600. Min Act: -0.1700
Data Index: 3666172 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.4600. Min Act: -0.1700
Data Index: 1384042 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.3975. Min Act: -0.1700
Data Index: 4025547 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.4288. Min Act: -0.1700
Data Index: 1470949 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0850. Min Range: -5.0850
Max Act: 4.4288. Min Act: -0.1700
Data Index: 4433828 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19