Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.3479. Min Act: -0.1700
Data Index: 13820 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.2541. Min Act: -0.1700
Data Index: 7125318 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.1604. Min Act: -0.1700
Data Index: 6944252 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.1604. Min Act: -0.1700
Data Index: 5716737 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.0666. Min Act: -0.1700
Data Index: 5398971 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.0353. Min Act: -0.1700
Data Index: 54163 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3479. Min Range: -4.3479
Max Act: 3.9728. Min Act: -0.1700
Data Index: 3603549 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.0353. Min Act: -0.1700
Data Index: 855942 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.0041. Min Act: -0.1700
Data Index: 8156212 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.0353. Min Act: -0.1700
Data Index: 2461574 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.0041. Min Act: -0.1700
Data Index: 7934807 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.0041. Min Act: -0.1700
Data Index: 8592977 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3479. Min Range: -4.3479
Max Act: 4.0353. Min Act: -0.1700
Data Index: 7613973 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3479. Min Range: -4.3479
Max Act: 3.9728. Min Act: -0.1700
Data Index: 2333743 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3479. Min Range: -4.3479
Max Act: 3.9416. Min Act: -0.1700
Data Index: 4801679 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3479. Min Range: -4.3479
Max Act: 3.9728. Min Act: -0.1700
Data Index: 7171116 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3479. Min Range: -4.3479
Max Act: 3.9416. Min Act: -0.1700
Data Index: 2158137 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3479. Min Range: -4.3479
Max Act: 3.9728. Min Act: -0.1700
Data Index: 8099694 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3479. Min Range: -4.3479
Max Act: 3.9416. Min Act: -0.1700
Data Index: 450374 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3479. Min Range: -4.3479
Max Act: 3.9416. Min Act: -0.1700
Data Index: 3896642 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19