Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3327 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0258. Min Range: -6.0258
Max Act: 6.0258. Min Act: -0.1700
Data Index: 6120142 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.8696. Min Act: -0.1700
Data Index: 366771 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.8071. Min Act: -0.1700
Data Index: 8201344 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.6821. Min Act: -0.1700
Data Index: 5213107 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.6821. Min Act: -0.1700
Data Index: 8805817 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.6821. Min Act: -0.1700
Data Index: 1747080 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.6508. Min Act: -0.1700
Data Index: 2098226 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.6508. Min Act: -0.1700
Data Index: 1189286 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.6196. Min Act: -0.1700
Data Index: 5920358 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.5883. Min Act: -0.1700
Data Index: 2080620 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.6196. Min Act: -0.1700
Data Index: 1439141 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.5571. Min Act: -0.1700
Data Index: 7860592 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.5883. Min Act: -0.1700
Data Index: 7794105 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.5258. Min Act: -0.1700
Data Index: 6237325 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.5571. Min Act: -0.1700
Data Index: 5161723 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.5571. Min Act: -0.1700
Data Index: 2075757 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.5258. Min Act: -0.1700
Data Index: 7651612 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.5571. Min Act: -0.1700
Data Index: 1811020 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.5571. Min Act: -0.1700
Data Index: 6945360 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0258. Min Range: -6.0258
Max Act: 5.5571. Min Act: -0.1700
Data Index: 3167040 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19