Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5157 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0018. Min Range: -8.0018
Max Act: 8.0018. Min Act: -0.1700
Data Index: 7085265 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.9706. Min Act: -0.1700
Data Index: 4976072 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.8768. Min Act: -0.1700
Data Index: 2416958 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.8143. Min Act: -0.1700
Data Index: 3594894 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.8143. Min Act: -0.1700
Data Index: 3975649 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.7831. Min Act: -0.1700
Data Index: 6784620 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.7831. Min Act: -0.1700
Data Index: 4511606 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.7518. Min Act: -0.1700
Data Index: 5789856 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.7206. Min Act: -0.1700
Data Index: 2414857 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.6581. Min Act: -0.1700
Data Index: 2785417 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.6893. Min Act: -0.1700
Data Index: 555143 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.6581. Min Act: -0.1700
Data Index: 12413 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.5018. Min Act: -0.1700
Data Index: 5675837 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.5331. Min Act: -0.1700
Data Index: 6737622 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.4706. Min Act: -0.1700
Data Index: 8422868 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.4706. Min Act: -0.1700
Data Index: 4915260 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.4393. Min Act: -0.1700
Data Index: 7686014 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.4081. Min Act: -0.1700
Data Index: 3057725 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.4081. Min Act: -0.1700
Data Index: 4478706 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0018. Min Range: -8.0018
Max Act: 7.4081. Min Act: -0.1700
Data Index: 7705390 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19