Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1008 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1607. Min Range: -6.1607
Max Act: 6.1607. Min Act: -0.1700
Data Index: 8812271 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1607. Min Range: -6.1607
Max Act: 6.0670. Min Act: -0.1700
Data Index: 5185099 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1607. Min Range: -6.1607
Max Act: 6.0982. Min Act: -0.1700
Data Index: 3933375 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.9107. Min Act: -0.1700
Data Index: 1184189 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.9107. Min Act: -0.1700
Data Index: 7938519 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.8482. Min Act: -0.1700
Data Index: 6100464 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.8170. Min Act: -0.1700
Data Index: 798512 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.7545. Min Act: -0.1700
Data Index: 5868408 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.7545. Min Act: -0.1700
Data Index: 6262427 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.7232. Min Act: -0.1700
Data Index: 5718139 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.6607. Min Act: -0.1700
Data Index: 4869643 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.6607. Min Act: -0.1700
Data Index: 7211228 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.6295. Min Act: -0.1700
Data Index: 5731084 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.6607. Min Act: -0.1700
Data Index: 3311126 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.6295. Min Act: -0.1700
Data Index: 5697876 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.6295. Min Act: -0.1700
Data Index: 5002060 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.6295. Min Act: -0.1700
Data Index: 2073575 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.5982. Min Act: -0.1700
Data Index: 6804997 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.5982. Min Act: -0.1700
Data Index: 6934611 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1607. Min Range: -6.1607
Max Act: 5.5670. Min Act: -0.1700
Data Index: 2562116 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19