Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0925. Min Range: -7.0925
Max Act: 7.0925. Min Act: -0.1700
Data Index: 3668607 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0925. Min Range: -7.0925
Max Act: 7.0925. Min Act: -0.1700
Data Index: 8575721 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.9362. Min Act: -0.1700
Data Index: 7108719 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.8425. Min Act: -0.1700
Data Index: 7392924 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.8425. Min Act: -0.1700
Data Index: 639635 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.8112. Min Act: -0.1700
Data Index: 8345213 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.7800. Min Act: -0.1700
Data Index: 5314032 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.8112. Min Act: -0.1700
Data Index: 2535966 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.7800. Min Act: -0.1700
Data Index: 1912680 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.7175. Min Act: -0.1700
Data Index: 5649865 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.6237. Min Act: -0.1700
Data Index: 2347003 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.6550. Min Act: -0.1700
Data Index: 3341092 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.6862. Min Act: -0.1700
Data Index: 5804184 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.6237. Min Act: -0.1700
Data Index: 2347001 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.6237. Min Act: -0.1700
Data Index: 1905043 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.6550. Min Act: -0.1700
Data Index: 400084 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.5925. Min Act: -0.1700
Data Index: 8158011 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.5925. Min Act: -0.1700
Data Index: 5443830 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.5925. Min Act: -0.1700
Data Index: 705499 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0925. Min Range: -7.0925
Max Act: 6.5925. Min Act: -0.1700
Data Index: 592255 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19