Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5938 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0174. Min Range: -10.0174
Max Act: 10.0174. Min Act: -0.1700
Data Index: 3052058 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.7049. Min Act: -0.1700
Data Index: 3837750 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.6424. Min Act: -0.1700
Data Index: 8359323 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.5799. Min Act: -0.1700
Data Index: 5443994 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.4549. Min Act: -0.1700
Data Index: 3606534 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.4549. Min Act: -0.1700
Data Index: 1947305 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.3924. Min Act: -0.1700
Data Index: 5109445 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.3299. Min Act: -0.1700
Data Index: 1418900 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.2674. Min Act: -0.1700
Data Index: 2753398 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.2049. Min Act: -0.1700
Data Index: 3187314 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.2049. Min Act: -0.1700
Data Index: 4839408 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.1424. Min Act: -0.1700
Data Index: 3069656 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.1424. Min Act: -0.1700
Data Index: 2766989 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.1424. Min Act: -0.1700
Data Index: 4391039 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.1424. Min Act: -0.1700
Data Index: 4839410 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.0799. Min Act: -0.1700
Data Index: 6155864 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.0799. Min Act: -0.1700
Data Index: 2288407 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.0799. Min Act: -0.1700
Data Index: 6685531 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.0799. Min Act: -0.1700
Data Index: 1860001 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0174. Min Range: -10.0174
Max Act: 9.0174. Min Act: -0.1700
Data Index: 1007158 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19