Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.7175. Min Act: -0.1700
Data Index: 1555043 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.5407. Min Act: -0.1700
Data Index: 7382785 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.5084. Min Act: -0.1700
Data Index: 8612936 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.5246. Min Act: -0.1700
Data Index: 7111472 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4922. Min Act: -0.1700
Data Index: 6172719 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4922. Min Act: -0.1700
Data Index: 4042356 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4922. Min Act: -0.1700
Data Index: 4457407 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4922. Min Act: -0.1700
Data Index: 5101049 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4760. Min Act: -0.1700
Data Index: 2213819 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4597. Min Act: -0.1700
Data Index: 3264176 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4760. Min Act: -0.1700
Data Index: 7753408 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4760. Min Act: -0.1700
Data Index: 6450683 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4272. Min Act: -0.1700
Data Index: 1133847 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4435. Min Act: -0.1700
Data Index: 398214 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4435. Min Act: -0.1700
Data Index: 4783447 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4435. Min Act: -0.1700
Data Index: 564493 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4597. Min Act: -0.1700
Data Index: 6789720 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4597. Min Act: -0.1700
Data Index: 7607064 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4435. Min Act: -0.1700
Data Index: 2007780 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7175. Min Range: -2.7175
Max Act: 2.4435. Min Act: -0.1700
Data Index: 5896019 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19