Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4785 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.8588. Min Act: -0.1700
Data Index: 8698484 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.7651. Min Act: -0.1700
Data Index: 2318673 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.7651. Min Act: -0.1700
Data Index: 3849594 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.7338. Min Act: -0.1700
Data Index: 4937648 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.6401. Min Act: -0.1700
Data Index: 1210321 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.5776. Min Act: -0.1700
Data Index: 1693173 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.5463. Min Act: -0.1700
Data Index: 4758032 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.5151. Min Act: -0.1700
Data Index: 3002928 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.4838. Min Act: -0.1700
Data Index: 4482680 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.4526. Min Act: -0.1700
Data Index: 3792893 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.4526. Min Act: -0.1700
Data Index: 2316881 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.4526. Min Act: -0.1700
Data Index: 7943645 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.4526. Min Act: -0.1700
Data Index: 3624121 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.3901. Min Act: -0.1700
Data Index: 1480069 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.4213. Min Act: -0.1700
Data Index: 1528424 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.3901. Min Act: -0.1700
Data Index: 4320118 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.4213. Min Act: -0.1700
Data Index: 6602018 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.3901. Min Act: -0.1700
Data Index: 5687307 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.3901. Min Act: -0.1700
Data Index: 3689992 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8588. Min Range: -4.8588
Max Act: 4.3588. Min Act: -0.1700
Data Index: 7025918 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19