Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1695. Min Range: -6.1695
Max Act: 6.1695. Min Act: -0.1700
Data Index: 81005 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1695. Min Range: -6.1695
Max Act: 6.1695. Min Act: -0.1700
Data Index: 747172 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1695. Min Range: -6.1695
Max Act: 6.0445. Min Act: -0.1700
Data Index: 764080 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.9820. Min Act: -0.1700
Data Index: 5162405 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.8570. Min Act: -0.1700
Data Index: 81008 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.8257. Min Act: -0.1700
Data Index: 1715636 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.7632. Min Act: -0.1700
Data Index: 6116866 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.7320. Min Act: -0.1700
Data Index: 3361066 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.7320. Min Act: -0.1700
Data Index: 7250788 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.7007. Min Act: -0.1700
Data Index: 5485287 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.6695. Min Act: -0.1700
Data Index: 8441575 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.5757. Min Act: -0.1700
Data Index: 5162407 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.5132. Min Act: -0.1700
Data Index: 6617298 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.5132. Min Act: -0.1700
Data Index: 291513 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.5132. Min Act: -0.1700
Data Index: 3415705 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.5132. Min Act: -0.1700
Data Index: 3219485 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.5445. Min Act: -0.1700
Data Index: 617767 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.4820. Min Act: -0.1700
Data Index: 4313297 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.4820. Min Act: -0.1700
Data Index: 6540875 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1695. Min Range: -6.1695
Max Act: 5.3570. Min Act: -0.1700
Data Index: 4117009 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19