Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3954 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.4671. Min Act: -0.1700
Data Index: 915856 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.3733. Min Act: -0.1700
Data Index: 7135822 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.2171. Min Act: -0.1700
Data Index: 2012900 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.2483. Min Act: -0.1700
Data Index: 1335495 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.2171. Min Act: -0.1700
Data Index: 4674729 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.1858. Min Act: -0.1700
Data Index: 1960145 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.1858. Min Act: -0.1700
Data Index: 1538939 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.1858. Min Act: -0.1700
Data Index: 1302531 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.1858. Min Act: -0.1700
Data Index: 6006166 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.1546. Min Act: -0.1700
Data Index: 6303173 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.1233. Min Act: -0.1700
Data Index: 178005 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.1233. Min Act: -0.1700
Data Index: 5759169 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.1233. Min Act: -0.1700
Data Index: 1698242 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.1233. Min Act: -0.1700
Data Index: 7654602 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.1233. Min Act: -0.1700
Data Index: 3572876 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.0921. Min Act: -0.1700
Data Index: 3236798 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.0608. Min Act: -0.1700
Data Index: 4270009 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.0295. Min Act: -0.1700
Data Index: 2126253 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.0608. Min Act: -0.1700
Data Index: 3168133 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4671. Min Range: -4.4671
Max Act: 4.0295. Min Act: -0.1700
Data Index: 6477861 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19