Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 67 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.6625. Min Act: -0.1700
Data Index: 963006 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.6312. Min Act: -0.1700
Data Index: 7260961 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.5999. Min Act: -0.1700
Data Index: 7170639 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.5842. Min Act: -0.1700
Data Index: 3209105 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.5373. Min Act: -0.1700
Data Index: 8500331 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.5059. Min Act: -0.1700
Data Index: 4540431 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4746. Min Act: -0.1700
Data Index: 618735 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4589. Min Act: -0.1700
Data Index: 60252 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4589. Min Act: -0.1700
Data Index: 1522066 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4589. Min Act: -0.1700
Data Index: 4719888 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4589. Min Act: -0.1700
Data Index: 7465096 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4433. Min Act: -0.1700
Data Index: 548783 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4746. Min Act: -0.1700
Data Index: 8634888 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4589. Min Act: -0.1700
Data Index: 6616305 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4433. Min Act: -0.1700
Data Index: 2699793 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4276. Min Act: -0.1700
Data Index: 7718672 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4433. Min Act: -0.1700
Data Index: 1757242 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4433. Min Act: -0.1700
Data Index: 3851151 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4433. Min Act: -0.1700
Data Index: 6403433 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6625. Min Range: -3.6625
Max Act: 3.4276. Min Act: -0.1700
Data Index: 3767215 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19