Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 372 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.2703. Min Act: -0.1700
Data Index: 1479668 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.2078. Min Act: -0.1700
Data Index: 1865593 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.1765. Min Act: -0.1700
Data Index: 8484496 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.1140. Min Act: -0.1700
Data Index: 2863689 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.1140. Min Act: -0.1700
Data Index: 7500382 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.0515. Min Act: -0.1700
Data Index: 4608066 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.0828. Min Act: -0.1700
Data Index: 6416404 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.0515. Min Act: -0.1700
Data Index: 5406202 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.0203. Min Act: -0.1700
Data Index: 3531516 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.0203. Min Act: -0.1700
Data Index: 2189499 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.0203. Min Act: -0.1700
Data Index: 7907131 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.0203. Min Act: -0.1700
Data Index: 2289806 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.0515. Min Act: -0.1700
Data Index: 6408501 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9890. Min Act: -0.1700
Data Index: 6469355 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9890. Min Act: -0.1700
Data Index: 4337721 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9890. Min Act: -0.1700
Data Index: 7094075 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9578. Min Act: -0.1700
Data Index: 3261057 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9578. Min Act: -0.1700
Data Index: 3847391 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9890. Min Act: -0.1700
Data Index: 533053 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9265. Min Act: -0.1700
Data Index: 6740886 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19