Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.6755. Min Act: -0.1700
Data Index: 275731 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.6443. Min Act: -0.1700
Data Index: 4428712 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.6130. Min Act: -0.1700
Data Index: 8148620 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.5505. Min Act: -0.1700
Data Index: 698018 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.5818. Min Act: -0.1700
Data Index: 888204 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.5505. Min Act: -0.1700
Data Index: 5889786 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.5505. Min Act: -0.1700
Data Index: 5927954 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4880. Min Act: -0.1700
Data Index: 4397510 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4568. Min Act: -0.1700
Data Index: 5084949 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4568. Min Act: -0.1700
Data Index: 5655137 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4568. Min Act: -0.1700
Data Index: 1555895 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4568. Min Act: -0.1700
Data Index: 4374575 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4568. Min Act: -0.1700
Data Index: 5841327 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4568. Min Act: -0.1700
Data Index: 3917207 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4255. Min Act: -0.1700
Data Index: 3103157 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4255. Min Act: -0.1700
Data Index: 7654881 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4255. Min Act: -0.1700
Data Index: 3115749 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4255. Min Act: -0.1700
Data Index: 8148615 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4255. Min Act: -0.1700
Data Index: 3550309 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6755. Min Range: -4.6755
Max Act: 4.4255. Min Act: -0.1700
Data Index: 1559462 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19