Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3079. Min Range: -7.3079
Max Act: 7.3079. Min Act: -0.1700
Data Index: 2378207 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3079. Min Range: -7.3079
Max Act: 7.1829. Min Act: -0.1700
Data Index: 1986645 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3079. Min Range: -7.3079
Max Act: 7.0579. Min Act: -0.1700
Data Index: 5515309 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3079. Min Range: -7.3079
Max Act: 7.0266. Min Act: -0.1700
Data Index: 8312106 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3079. Min Range: -7.3079
Max Act: 7.0579. Min Act: -0.1700
Data Index: 4942299 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9954. Min Act: -0.1700
Data Index: 4492660 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3079. Min Range: -7.3079
Max Act: 7.0266. Min Act: -0.1700
Data Index: 4888122 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9954. Min Act: -0.1700
Data Index: 8529233 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9954. Min Act: -0.1700
Data Index: 3710264 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9641. Min Act: -0.1700
Data Index: 6693974 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9329. Min Act: -0.1700
Data Index: 2771518 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9641. Min Act: -0.1700
Data Index: 6493305 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9641. Min Act: -0.1700
Data Index: 2466914 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9641. Min Act: -0.1700
Data Index: 7487937 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9016. Min Act: -0.1700
Data Index: 6885001 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9016. Min Act: -0.1700
Data Index: 6315257 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9329. Min Act: -0.1700
Data Index: 3393486 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9016. Min Act: -0.1700
Data Index: 3422946 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9016. Min Act: -0.1700
Data Index: 6521719 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3079. Min Range: -7.3079
Max Act: 6.9016. Min Act: -0.1700
Data Index: 5012129 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19