Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1883 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.4799. Min Act: -0.1700
Data Index: 7765723 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.4799. Min Act: -0.1700
Data Index: 8617518 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.3237. Min Act: -0.1700
Data Index: 401246 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.2924. Min Act: -0.1700
Data Index: 3999077 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.2299. Min Act: -0.1700
Data Index: 1359399 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.2299. Min Act: -0.1700
Data Index: 4428256 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.2612. Min Act: -0.1700
Data Index: 7119548 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.2299. Min Act: -0.1700
Data Index: 6836559 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.2299. Min Act: -0.1700
Data Index: 4324482 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.1987. Min Act: -0.1700
Data Index: 762163 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.1987. Min Act: -0.1700
Data Index: 8483200 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.1987. Min Act: -0.1700
Data Index: 7620762 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.1674. Min Act: -0.1700
Data Index: 3284581 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.1674. Min Act: -0.1700
Data Index: 2018422 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.1362. Min Act: -0.1700
Data Index: 8665015 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.1674. Min Act: -0.1700
Data Index: 6651678 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.1049. Min Act: -0.1700
Data Index: 5416537 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.1362. Min Act: -0.1700
Data Index: 5212158 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.1049. Min Act: -0.1700
Data Index: 6272657 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4799. Min Range: -5.4799
Max Act: 5.0737. Min Act: -0.1700
Data Index: 1609577 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19