Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 997 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0374. Min Range: -5.0374
Max Act: 5.0374. Min Act: -0.1700
Data Index: 3575619 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0374. Min Range: -5.0374
Max Act: 5.0374. Min Act: -0.1700
Data Index: 1039631 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0374. Min Range: -5.0374
Max Act: 5.0061. Min Act: -0.1700
Data Index: 1969408 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0374. Min Range: -5.0374
Max Act: 5.0061. Min Act: -0.1700
Data Index: 4458981 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0374. Min Range: -5.0374
Max Act: 5.0061. Min Act: -0.1700
Data Index: 7592814 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.9124. Min Act: -0.1700
Data Index: 2960239 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.9124. Min Act: -0.1700
Data Index: 1285265 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.8811. Min Act: -0.1700
Data Index: 5456436 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.8499. Min Act: -0.1700
Data Index: 4224645 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.8499. Min Act: -0.1700
Data Index: 7267493 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.8186. Min Act: -0.1700
Data Index: 5428371 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.8186. Min Act: -0.1700
Data Index: 6379129 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.7874. Min Act: -0.1700
Data Index: 240549 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.7874. Min Act: -0.1700
Data Index: 6201286 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.7874. Min Act: -0.1700
Data Index: 4162248 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.7874. Min Act: -0.1700
Data Index: 4115852 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.7561. Min Act: -0.1700
Data Index: 2673047 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.7874. Min Act: -0.1700
Data Index: 3652452 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.7874. Min Act: -0.1700
Data Index: 8792534 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0374. Min Range: -5.0374
Max Act: 4.7874. Min Act: -0.1700
Data Index: 7195929 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19