Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4062 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.2632. Min Act: -0.1700
Data Index: 2561039 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.2320. Min Act: -0.1700
Data Index: 6196854 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.2320. Min Act: -0.1700
Data Index: 4290885 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.1382. Min Act: -0.1700
Data Index: 8542424 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.1382. Min Act: -0.1700
Data Index: 6738076 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.1382. Min Act: -0.1700
Data Index: 6411584 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.0445. Min Act: -0.1700
Data Index: 4360633 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.0445. Min Act: -0.1700
Data Index: 2035137 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.0445. Min Act: -0.1700
Data Index: 4621298 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.0132. Min Act: -0.1700
Data Index: 6608974 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.0132. Min Act: -0.1700
Data Index: 2473938 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.0132. Min Act: -0.1700
Data Index: 456540 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2632. Min Range: -5.2632
Max Act: 4.9820. Min Act: -0.1700
Data Index: 1906290 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2632. Min Range: -5.2632
Max Act: 5.0132. Min Act: -0.1700
Data Index: 401865 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2632. Min Range: -5.2632
Max Act: 4.9507. Min Act: -0.1700
Data Index: 5162542 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2632. Min Range: -5.2632
Max Act: 4.9507. Min Act: -0.1700
Data Index: 8355643 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2632. Min Range: -5.2632
Max Act: 4.9195. Min Act: -0.1700
Data Index: 5325491 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2632. Min Range: -5.2632
Max Act: 4.8882. Min Act: -0.1700
Data Index: 3285483 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2632. Min Range: -5.2632
Max Act: 4.9195. Min Act: -0.1700
Data Index: 7228692 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2632. Min Range: -5.2632
Max Act: 4.8570. Min Act: -0.1700
Data Index: 2601167 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19