Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.6605. Min Act: -0.1700
Data Index: 5057707 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.5355. Min Act: -0.1700
Data Index: 8398660 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.4730. Min Act: -0.1700
Data Index: 6414001 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.4730. Min Act: -0.1700
Data Index: 150957 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.4418. Min Act: -0.1700
Data Index: 1043631 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.4105. Min Act: -0.1700
Data Index: 8385012 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.3793. Min Act: -0.1700
Data Index: 1640572 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.3793. Min Act: -0.1700
Data Index: 4648095 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.3168. Min Act: -0.1700
Data Index: 7994604 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.2855. Min Act: -0.1700
Data Index: 1191140 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.3168. Min Act: -0.1700
Data Index: 8145040 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.2855. Min Act: -0.1700
Data Index: 8592531 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.2855. Min Act: -0.1700
Data Index: 4054495 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.2855. Min Act: -0.1700
Data Index: 3212340 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.2855. Min Act: -0.1700
Data Index: 3767283 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.2543. Min Act: -0.1700
Data Index: 725722 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.2855. Min Act: -0.1700
Data Index: 3444996 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.2230. Min Act: -0.1700
Data Index: 370075 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.2230. Min Act: -0.1700
Data Index: 2716545 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6605. Min Range: -5.6605
Max Act: 5.2230. Min Act: -0.1700
Data Index: 6087501 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19