Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2710 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.4641. Min Act: -0.1700
Data Index: 838397 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.4329. Min Act: -0.1700
Data Index: 2012510 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.3391. Min Act: -0.1700
Data Index: 8139646 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.3078. Min Act: -0.1700
Data Index: 341510 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.3078. Min Act: -0.1700
Data Index: 3926087 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.3078. Min Act: -0.1700
Data Index: 3761440 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2766. Min Act: -0.1700
Data Index: 6872549 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2766. Min Act: -0.1700
Data Index: 3287451 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2766. Min Act: -0.1700
Data Index: 3445221 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2766. Min Act: -0.1700
Data Index: 205054 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2766. Min Act: -0.1700
Data Index: 2131932 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2141. Min Act: -0.1700
Data Index: 686979 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2453. Min Act: -0.1700
Data Index: 8718573 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2453. Min Act: -0.1700
Data Index: 3883074 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2766. Min Act: -0.1700
Data Index: 7910623 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2766. Min Act: -0.1700
Data Index: 7246790 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2453. Min Act: -0.1700
Data Index: 351653 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2453. Min Act: -0.1700
Data Index: 6126613 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2453. Min Act: -0.1700
Data Index: 7592456 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4641. Min Range: -4.4641
Max Act: 4.2141. Min Act: -0.1700
Data Index: 2269675 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19