Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 820 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.9668. Min Act: -0.1700
Data Index: 1672240 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.9043. Min Act: -0.1700
Data Index: 6214518 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.8105. Min Act: -0.1700
Data Index: 2988371 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.7168. Min Act: -0.1700
Data Index: 4545279 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.7793. Min Act: -0.1700
Data Index: 734790 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.5918. Min Act: -0.1700
Data Index: 5753436 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.6230. Min Act: -0.1700
Data Index: 4846998 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.5605. Min Act: -0.1700
Data Index: 2843373 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.4668. Min Act: -0.1700
Data Index: 193349 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.4355. Min Act: -0.1700
Data Index: 7278077 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.3418. Min Act: -0.1700
Data Index: 1180709 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.3418. Min Act: -0.1700
Data Index: 6241186 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.3105. Min Act: -0.1700
Data Index: 2996383 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.2168. Min Act: -0.1700
Data Index: 6190907 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.2480. Min Act: -0.1700
Data Index: 5138530 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.1230. Min Act: -0.1700
Data Index: 3406239 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.1230. Min Act: -0.1700
Data Index: 3257252 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.0918. Min Act: -0.1700
Data Index: 736468 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.0918. Min Act: -0.1700
Data Index: 1442764 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9668. Min Range: -6.9668
Max Act: 6.0918. Min Act: -0.1700
Data Index: 5581237 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19