Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1530 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.3467. Min Act: -0.1700
Data Index: 1733962 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.3311. Min Act: -0.1700
Data Index: 1733961 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.2526. Min Act: -0.1700
Data Index: 8421780 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.2840. Min Act: -0.1700
Data Index: 8421781 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.1739. Min Act: -0.1700
Data Index: 245033 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.1739. Min Act: -0.1700
Data Index: 1733963 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.1739. Min Act: -0.1700
Data Index: 8421782 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.1582. Min Act: -0.1700
Data Index: 4531426 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.1110. Min Act: -0.1700
Data Index: 1733964 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.1425. Min Act: -0.1700
Data Index: 2698923 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.1110. Min Act: -0.1700
Data Index: 5392568 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.0479. Min Act: -0.1700
Data Index: 2947523 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.0794. Min Act: -0.1700
Data Index: 2981913 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.0794. Min Act: -0.1700
Data Index: 6506810 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.0637. Min Act: -0.1700
Data Index: 4799016 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.0637. Min Act: -0.1700
Data Index: 5392570 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.0005. Min Act: -0.1700
Data Index: 1324639 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.0479. Min Act: -0.1700
Data Index: 1714469 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.0637. Min Act: -0.1700
Data Index: 7238487 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3467. Min Range: -3.3467
Max Act: 3.0794. Min Act: -0.1700
Data Index: 1733959 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19