Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 987 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1898. Min Range: -5.1898
Max Act: 5.1585. Min Act: -0.1700
Data Index: 8594058 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1898. Min Range: -5.1898
Max Act: 5.1898. Min Act: -0.1700
Data Index: 5041764 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1898. Min Range: -5.1898
Max Act: 5.1273. Min Act: -0.1700
Data Index: 2834320 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1898. Min Range: -5.1898
Max Act: 5.0648. Min Act: -0.1700
Data Index: 1799969 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1898. Min Range: -5.1898
Max Act: 5.0648. Min Act: -0.1700
Data Index: 3392868 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1898. Min Range: -5.1898
Max Act: 5.0960. Min Act: -0.1700
Data Index: 3968279 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1898. Min Range: -5.1898
Max Act: 5.0335. Min Act: -0.1700
Data Index: 2764481 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1898. Min Range: -5.1898
Max Act: 5.0648. Min Act: -0.1700
Data Index: 8771537 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1898. Min Range: -5.1898
Max Act: 5.0648. Min Act: -0.1700
Data Index: 4205163 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1898. Min Range: -5.1898
Max Act: 4.9710. Min Act: -0.1700
Data Index: 6340594 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1898. Min Range: -5.1898
Max Act: 4.9710. Min Act: -0.1700
Data Index: 4612089 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1898. Min Range: -5.1898
Max Act: 4.9398. Min Act: -0.1700
Data Index: 3930888 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1898. Min Range: -5.1898
Max Act: 4.9710. Min Act: -0.1700
Data Index: 6328829 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1898. Min Range: -5.1898
Max Act: 4.9398. Min Act: -0.1700
Data Index: 5367379 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1898. Min Range: -5.1898
Max Act: 4.9398. Min Act: -0.1700
Data Index: 3831976 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1898. Min Range: -5.1898
Max Act: 4.9085. Min Act: -0.1700
Data Index: 7016038 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1898. Min Range: -5.1898
Max Act: 4.9085. Min Act: -0.1700
Data Index: 7660011 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1898. Min Range: -5.1898
Max Act: 4.8773. Min Act: -0.1700
Data Index: 8004447 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1898. Min Range: -5.1898
Max Act: 4.8773. Min Act: -0.1700
Data Index: 908073 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1898. Min Range: -5.1898
Max Act: 4.8773. Min Act: -0.1700
Data Index: 5954017 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19