Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0664. Min Range: -5.0664
Max Act: 5.0664. Min Act: -0.1700
Data Index: 2675948 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.9726. Min Act: -0.1700
Data Index: 2096816 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.9726. Min Act: -0.1700
Data Index: 5444168 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0664. Min Range: -5.0664
Max Act: 5.0039. Min Act: -0.1700
Data Index: 3422067 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.9414. Min Act: -0.1700
Data Index: 176087 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.9101. Min Act: -0.1700
Data Index: 4967504 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.8789. Min Act: -0.1700
Data Index: 963627 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.8789. Min Act: -0.1700
Data Index: 5030407 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.9101. Min Act: -0.1700
Data Index: 4625247 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.8164. Min Act: -0.1700
Data Index: 117256 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.8164. Min Act: -0.1700
Data Index: 5567587 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.8476. Min Act: -0.1700
Data Index: 7236135 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.8164. Min Act: -0.1700
Data Index: 5089210 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.8164. Min Act: -0.1700
Data Index: 5039657 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.7851. Min Act: -0.1700
Data Index: 4845810 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.7539. Min Act: -0.1700
Data Index: 3969779 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.7851. Min Act: -0.1700
Data Index: 3640229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.7851. Min Act: -0.1700
Data Index: 8643156 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.7539. Min Act: -0.1700
Data Index: 3999160 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0664. Min Range: -5.0664
Max Act: 4.7539. Min Act: -0.1700
Data Index: 714338 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19