Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1242 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.7920. Min Act: -0.1700
Data Index: 6875084 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.7607. Min Act: -0.1700
Data Index: 4876973 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6982. Min Act: -0.1700
Data Index: 6706243 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6670. Min Act: -0.1700
Data Index: 8157506 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6670. Min Act: -0.1700
Data Index: 7156727 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6670. Min Act: -0.1700
Data Index: 8144672 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6357. Min Act: -0.1700
Data Index: 6070607 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6357. Min Act: -0.1700
Data Index: 1538000 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6045. Min Act: -0.1700
Data Index: 3670285 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5732. Min Act: -0.1700
Data Index: 2893198 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6045. Min Act: -0.1700
Data Index: 905011 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5732. Min Act: -0.1700
Data Index: 2622396 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6045. Min Act: -0.1700
Data Index: 8792870 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5732. Min Act: -0.1700
Data Index: 4861721 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5732. Min Act: -0.1700
Data Index: 877252 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5732. Min Act: -0.1700
Data Index: 2413522 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5420. Min Act: -0.1700
Data Index: 47161 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5420. Min Act: -0.1700
Data Index: 4887054 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5420. Min Act: -0.1700
Data Index: 4027105 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5107. Min Act: -0.1700
Data Index: 3334204 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19