Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.3619. Min Act: -0.1700
Data Index: 1211267 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.3931. Min Act: -0.1700
Data Index: 4175583 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.3619. Min Act: -0.1700
Data Index: 6726769 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.3931. Min Act: -0.1700
Data Index: 8648874 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.3619. Min Act: -0.1700
Data Index: 71435 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.2681. Min Act: -0.1700
Data Index: 1384395 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.2369. Min Act: -0.1700
Data Index: 2152714 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.4556. Min Act: -0.1700
Data Index: 5983003 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.1431. Min Act: -0.1700
Data Index: 8265064 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.0806. Min Act: -0.1700
Data Index: 387238 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.1119. Min Act: -0.1700
Data Index: 4140138 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.0181. Min Act: -0.1700
Data Index: 4559110 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.0806. Min Act: -0.1700
Data Index: 1251203 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.0181. Min Act: -0.1700
Data Index: 1486351 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.0806. Min Act: -0.1700
Data Index: 776335 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.9869. Min Act: -0.1700
Data Index: 4563592 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.9869. Min Act: -0.1700
Data Index: 288210 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3931. Min Range: -6.3931
Max Act: 6.0181. Min Act: -0.1700
Data Index: 6929846 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.9869. Min Act: -0.1700
Data Index: 5911981 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3931. Min Range: -6.3931
Max Act: 5.9556. Min Act: -0.1700
Data Index: 1719908 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19