Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4604 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4799. Min Range: -6.4799
Max Act: 6.4799. Min Act: -0.1700
Data Index: 5904194 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4799. Min Range: -6.4799
Max Act: 6.4486. Min Act: -0.1700
Data Index: 576638 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4799. Min Range: -6.4799
Max Act: 6.2611. Min Act: -0.1700
Data Index: 6620775 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4799. Min Range: -6.4799
Max Act: 6.1361. Min Act: -0.1700
Data Index: 384633 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4799. Min Range: -6.4799
Max Act: 6.0736. Min Act: -0.1700
Data Index: 5583296 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4799. Min Range: -6.4799
Max Act: 6.0736. Min Act: -0.1700
Data Index: 2693210 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4799. Min Range: -6.4799
Max Act: 6.0111. Min Act: -0.1700
Data Index: 3971653 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4799. Min Range: -6.4799
Max Act: 6.0424. Min Act: -0.1700
Data Index: 8504800 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.9799. Min Act: -0.1700
Data Index: 211814 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.9799. Min Act: -0.1700
Data Index: 1262454 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.9799. Min Act: -0.1700
Data Index: 73499 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.9486. Min Act: -0.1700
Data Index: 1124259 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.9174. Min Act: -0.1700
Data Index: 8565629 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.8549. Min Act: -0.1700
Data Index: 6323141 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.8549. Min Act: -0.1700
Data Index: 6174948 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.8549. Min Act: -0.1700
Data Index: 6381963 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.7611. Min Act: -0.1700
Data Index: 3000981 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.7611. Min Act: -0.1700
Data Index: 8155163 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.7924. Min Act: -0.1700
Data Index: 3284328 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4799. Min Range: -6.4799
Max Act: 5.7299. Min Act: -0.1700
Data Index: 5241219 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19