Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.3004. Min Act: -0.1700
Data Index: 8169492 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.2067. Min Act: -0.1700
Data Index: 7136565 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.1442. Min Act: -0.1700
Data Index: 6247434 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.1129. Min Act: -0.1700
Data Index: 8777142 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.1129. Min Act: -0.1700
Data Index: 6609407 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.0817. Min Act: -0.1700
Data Index: 2262070 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.1129. Min Act: -0.1700
Data Index: 8282804 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.0817. Min Act: -0.1700
Data Index: 5201678 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.0817. Min Act: -0.1700
Data Index: 8448480 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.0817. Min Act: -0.1700
Data Index: 6785611 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.0504. Min Act: -0.1700
Data Index: 66267 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.0192. Min Act: -0.1700
Data Index: 6425737 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.0192. Min Act: -0.1700
Data Index: 6673750 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.0192. Min Act: -0.1700
Data Index: 856011 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.0192. Min Act: -0.1700
Data Index: 2258309 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3004. Min Range: -6.3004
Max Act: 6.0192. Min Act: -0.1700
Data Index: 4821062 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3004. Min Range: -6.3004
Max Act: 5.9879. Min Act: -0.1700
Data Index: 7564712 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3004. Min Range: -6.3004
Max Act: 5.9567. Min Act: -0.1700
Data Index: 543333 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3004. Min Range: -6.3004
Max Act: 5.9567. Min Act: -0.1700
Data Index: 7300389 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3004. Min Range: -6.3004
Max Act: 5.9567. Min Act: -0.1700
Data Index: 3594992 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19