Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1878. Min Range: -5.1878
Max Act: 5.1878. Min Act: -0.1700
Data Index: 4434618 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1878. Min Range: -5.1878
Max Act: 5.0003. Min Act: -0.1700
Data Index: 3207965 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.9378. Min Act: -0.1700
Data Index: 6571179 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1878. Min Range: -5.1878
Max Act: 5.0003. Min Act: -0.1700
Data Index: 3113379 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.9378. Min Act: -0.1700
Data Index: 7211808 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.9065. Min Act: -0.1700
Data Index: 706148 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.8753. Min Act: -0.1700
Data Index: 4176737 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.8753. Min Act: -0.1700
Data Index: 8757850 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.9065. Min Act: -0.1700
Data Index: 8088840 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.8753. Min Act: -0.1700
Data Index: 5014380 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.9065. Min Act: -0.1700
Data Index: 1682463 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.8128. Min Act: -0.1700
Data Index: 2364575 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.8440. Min Act: -0.1700
Data Index: 401966 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.8753. Min Act: -0.1700
Data Index: 7538023 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.8753. Min Act: -0.1700
Data Index: 4336831 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.9065. Min Act: -0.1700
Data Index: 4099590 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.8440. Min Act: -0.1700
Data Index: 6069513 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.8440. Min Act: -0.1700
Data Index: 5431574 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.8440. Min Act: -0.1700
Data Index: 4005899 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1878. Min Range: -5.1878
Max Act: 4.8440. Min Act: -0.1700
Data Index: 5008346 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19