Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1617 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.7508. Min Act: -0.1700
Data Index: 6818574 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.6883. Min Act: -0.1700
Data Index: 3428537 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.4383. Min Act: -0.1700
Data Index: 1897728 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.3758. Min Act: -0.1700
Data Index: 5119330 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.3133. Min Act: -0.1700
Data Index: 7267673 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.3758. Min Act: -0.1700
Data Index: 4670276 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.2508. Min Act: -0.1700
Data Index: 3648790 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.2508. Min Act: -0.1700
Data Index: 498271 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.2508. Min Act: -0.1700
Data Index: 7456568 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.2508. Min Act: -0.1700
Data Index: 7716750 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.2508. Min Act: -0.1700
Data Index: 4627618 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.1883. Min Act: -0.1700
Data Index: 8260589 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.1883. Min Act: -0.1700
Data Index: 4237764 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.1883. Min Act: -0.1700
Data Index: 6094996 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.1258. Min Act: -0.1700
Data Index: 1890703 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.1258. Min Act: -0.1700
Data Index: 1340979 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.0633. Min Act: -0.1700
Data Index: 6042512 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.0633. Min Act: -0.1700
Data Index: 5796067 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.0633. Min Act: -0.1700
Data Index: 7335041 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7508. Min Range: -8.7508
Max Act: 8.0633. Min Act: -0.1700
Data Index: 1398212 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19