Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3662 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3934. Min Range: -12.3934
Max Act: 12.3934. Min Act: -0.1700
Data Index: 4460028 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3934. Min Range: -12.3934
Max Act: 12.1434. Min Act: -0.1700
Data Index: 1558576 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.9559. Min Act: -0.1700
Data Index: 7583875 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.5809. Min Act: -0.1700
Data Index: 1444816 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.5809. Min Act: -0.1700
Data Index: 395129 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.4559. Min Act: -0.1700
Data Index: 7793883 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.4559. Min Act: -0.1700
Data Index: 8487279 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.3309. Min Act: -0.1700
Data Index: 8356037 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.3309. Min Act: -0.1700
Data Index: 6469817 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.2684. Min Act: -0.1700
Data Index: 2269657 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.2059. Min Act: -0.1700
Data Index: 1579493 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.2059. Min Act: -0.1700
Data Index: 7593120 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.1434. Min Act: -0.1700
Data Index: 6492993 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.1434. Min Act: -0.1700
Data Index: 6274579 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.1434. Min Act: -0.1700
Data Index: 964686 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.1434. Min Act: -0.1700
Data Index: 7910980 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.0809. Min Act: -0.1700
Data Index: 3071798 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.0809. Min Act: -0.1700
Data Index: 2293979 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.0809. Min Act: -0.1700
Data Index: 6714562 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3934. Min Range: -12.3934
Max Act: 11.0809. Min Act: -0.1700
Data Index: 3403942 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19