Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1807 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.7767. Min Act: -0.1700
Data Index: 1929939 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6203. Min Act: -0.1700
Data Index: 8765584 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6047. Min Act: -0.1700
Data Index: 4737375 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5890. Min Act: -0.1700
Data Index: 3530213 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5890. Min Act: -0.1700
Data Index: 689798 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5577. Min Act: -0.1700
Data Index: 516420 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5107. Min Act: -0.1700
Data Index: 6536672 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5264. Min Act: -0.1700
Data Index: 6731522 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5264. Min Act: -0.1700
Data Index: 1437691 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5107. Min Act: -0.1700
Data Index: 7235029 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5107. Min Act: -0.1700
Data Index: 2006646 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4951. Min Act: -0.1700
Data Index: 4097341 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4794. Min Act: -0.1700
Data Index: 2166320 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4794. Min Act: -0.1700
Data Index: 3419739 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4481. Min Act: -0.1700
Data Index: 1267578 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4481. Min Act: -0.1700
Data Index: 2385661 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4481. Min Act: -0.1700
Data Index: 3430447 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4637. Min Act: -0.1700
Data Index: 2152497 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4481. Min Act: -0.1700
Data Index: 976029 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4481. Min Act: -0.1700
Data Index: 8760366 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19