Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.5742. Min Act: -0.1700
Data Index: 4531924 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.4804. Min Act: -0.1700
Data Index: 2939234 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.3242. Min Act: -0.1700
Data Index: 763854 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.2929. Min Act: -0.1700
Data Index: 3094106 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.2929. Min Act: -0.1700
Data Index: 8666229 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.2304. Min Act: -0.1700
Data Index: 635541 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.2304. Min Act: -0.1700
Data Index: 552739 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.1679. Min Act: -0.1700
Data Index: 7213085 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.1679. Min Act: -0.1700
Data Index: 3141295 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.1367. Min Act: -0.1700
Data Index: 283560 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.1992. Min Act: -0.1700
Data Index: 3735740 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.1679. Min Act: -0.1700
Data Index: 2379527 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.1367. Min Act: -0.1700
Data Index: 5710171 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.1367. Min Act: -0.1700
Data Index: 4035036 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.1367. Min Act: -0.1700
Data Index: 2270678 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.1054. Min Act: -0.1700
Data Index: 55371 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.1054. Min Act: -0.1700
Data Index: 7050697 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.1054. Min Act: -0.1700
Data Index: 3179107 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.0742. Min Act: -0.1700
Data Index: 6984311 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5742. Min Range: -5.5742
Max Act: 5.0742. Min Act: -0.1700
Data Index: 2341965 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19