Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4080 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.6309. Min Act: -0.1700
Data Index: 7253198 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.5684. Min Act: -0.1700
Data Index: 8193395 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.5372. Min Act: -0.1700
Data Index: 2118711 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.4434. Min Act: -0.1700
Data Index: 8175949 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.4122. Min Act: -0.1700
Data Index: 2711565 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.3809. Min Act: -0.1700
Data Index: 5616861 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.3809. Min Act: -0.1700
Data Index: 3145066 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.3497. Min Act: -0.1700
Data Index: 3587556 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.2559. Min Act: -0.1700
Data Index: 8792058 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.2247. Min Act: -0.1700
Data Index: 6594803 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.2559. Min Act: -0.1700
Data Index: 4728369 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.1934. Min Act: -0.1700
Data Index: 6167145 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.1934. Min Act: -0.1700
Data Index: 3989619 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.1622. Min Act: -0.1700
Data Index: 5875522 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.1622. Min Act: -0.1700
Data Index: 25518 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.1309. Min Act: -0.1700
Data Index: 421816 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.0997. Min Act: -0.1700
Data Index: 7254675 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.0997. Min Act: -0.1700
Data Index: 33579 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.0684. Min Act: -0.1700
Data Index: 6255385 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6309. Min Range: -5.6309
Max Act: 5.0684. Min Act: -0.1700
Data Index: 2005158 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19