Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2032 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.9733. Min Act: -0.1700
Data Index: 6163804 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.9733. Min Act: -0.1700
Data Index: 6480184 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.8796. Min Act: -0.1700
Data Index: 8219142 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.6608. Min Act: -0.1700
Data Index: 102493 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.6608. Min Act: -0.1700
Data Index: 2103024 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.6296. Min Act: -0.1700
Data Index: 7939523 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.6296. Min Act: -0.1700
Data Index: 777544 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5671. Min Act: -0.1700
Data Index: 7004601 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.6296. Min Act: -0.1700
Data Index: 6945028 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5983. Min Act: -0.1700
Data Index: 4724237 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5671. Min Act: -0.1700
Data Index: 898165 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5983. Min Act: -0.1700
Data Index: 1924842 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5671. Min Act: -0.1700
Data Index: 5177359 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5671. Min Act: -0.1700
Data Index: 5160757 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5046. Min Act: -0.1700
Data Index: 732763 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5358. Min Act: -0.1700
Data Index: 4561756 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5671. Min Act: -0.1700
Data Index: 1315495 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5046. Min Act: -0.1700
Data Index: 5119191 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5046. Min Act: -0.1700
Data Index: 6072981 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9733. Min Range: -5.9733
Max Act: 5.5358. Min Act: -0.1700
Data Index: 8158025 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19