Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4392 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2930. Min Range: -5.2930
Max Act: 5.2930. Min Act: -0.1700
Data Index: 4981167 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2930. Min Range: -5.2930
Max Act: 5.1680. Min Act: -0.1700
Data Index: 3457140 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2930. Min Range: -5.2930
Max Act: 5.1993. Min Act: -0.1700
Data Index: 1298504 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2930. Min Range: -5.2930
Max Act: 5.1055. Min Act: -0.1700
Data Index: 2343536 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2930. Min Range: -5.2930
Max Act: 5.1055. Min Act: -0.1700
Data Index: 3658825 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2930. Min Range: -5.2930
Max Act: 5.0743. Min Act: -0.1700
Data Index: 6136144 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2930. Min Range: -5.2930
Max Act: 5.0430. Min Act: -0.1700
Data Index: 5544672 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2930. Min Range: -5.2930
Max Act: 5.0118. Min Act: -0.1700
Data Index: 3379783 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2930. Min Range: -5.2930
Max Act: 5.0118. Min Act: -0.1700
Data Index: 7550819 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2930. Min Range: -5.2930
Max Act: 4.9805. Min Act: -0.1700
Data Index: 1902442 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2930. Min Range: -5.2930
Max Act: 4.9493. Min Act: -0.1700
Data Index: 8041514 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2930. Min Range: -5.2930
Max Act: 4.9493. Min Act: -0.1700
Data Index: 5124174 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2930. Min Range: -5.2930
Max Act: 4.9180. Min Act: -0.1700
Data Index: 2485007 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2930. Min Range: -5.2930
Max Act: 4.9180. Min Act: -0.1700
Data Index: 2943478 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2930. Min Range: -5.2930
Max Act: 4.9493. Min Act: -0.1700
Data Index: 6676908 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2930. Min Range: -5.2930
Max Act: 4.8868. Min Act: -0.1700
Data Index: 3150105 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2930. Min Range: -5.2930
Max Act: 4.9180. Min Act: -0.1700
Data Index: 8163501 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2930. Min Range: -5.2930
Max Act: 4.9180. Min Act: -0.1700
Data Index: 1119349 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2930. Min Range: -5.2930
Max Act: 4.8868. Min Act: -0.1700
Data Index: 659247 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2930. Min Range: -5.2930
Max Act: 4.8868. Min Act: -0.1700
Data Index: 5609704 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19