Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4222 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.4118. Min Act: -0.1700
Data Index: 5796788 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.1618. Min Act: -0.1700
Data Index: 7075153 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.1305. Min Act: -0.1700
Data Index: 3862383 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.0993. Min Act: -0.1700
Data Index: 4638998 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.0993. Min Act: -0.1700
Data Index: 8023026 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.0993. Min Act: -0.1700
Data Index: 3309547 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.0680. Min Act: -0.1700
Data Index: 4934903 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.0680. Min Act: -0.1700
Data Index: 8639512 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.0680. Min Act: -0.1700
Data Index: 2997119 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.0368. Min Act: -0.1700
Data Index: 7106446 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.0055. Min Act: -0.1700
Data Index: 3537553 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.0055. Min Act: -0.1700
Data Index: 5558192 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4118. Min Range: -7.4118
Max Act: 7.0055. Min Act: -0.1700
Data Index: 8358093 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4118. Min Range: -7.4118
Max Act: 6.9743. Min Act: -0.1700
Data Index: 4514799 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4118. Min Range: -7.4118
Max Act: 6.9743. Min Act: -0.1700
Data Index: 1268559 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4118. Min Range: -7.4118
Max Act: 6.9118. Min Act: -0.1700
Data Index: 112466 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4118. Min Range: -7.4118
Max Act: 6.9430. Min Act: -0.1700
Data Index: 1586248 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4118. Min Range: -7.4118
Max Act: 6.9430. Min Act: -0.1700
Data Index: 2298733 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4118. Min Range: -7.4118
Max Act: 6.9430. Min Act: -0.1700
Data Index: 2327969 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4118. Min Range: -7.4118
Max Act: 6.9118. Min Act: -0.1700
Data Index: 4571454 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19