Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3686 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.5000. Min Act: -0.1700
Data Index: 4102783 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.3275. Min Act: -0.1700
Data Index: 4762032 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.3432. Min Act: -0.1700
Data Index: 251812 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2961. Min Act: -0.1700
Data Index: 3365439 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2961. Min Act: -0.1700
Data Index: 8286627 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2804. Min Act: -0.1700
Data Index: 2213755 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2490. Min Act: -0.1700
Data Index: 6005610 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2490. Min Act: -0.1700
Data Index: 6755352 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2490. Min Act: -0.1700
Data Index: 4204178 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2333. Min Act: -0.1700
Data Index: 3255717 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2490. Min Act: -0.1700
Data Index: 2516602 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2176. Min Act: -0.1700
Data Index: 5631128 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2333. Min Act: -0.1700
Data Index: 1122915 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2176. Min Act: -0.1700
Data Index: 3487759 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.1861. Min Act: -0.1700
Data Index: 3036945 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.2176. Min Act: -0.1700
Data Index: 2625527 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.1704. Min Act: -0.1700
Data Index: 6557155 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.1547. Min Act: -0.1700
Data Index: 8487027 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.1547. Min Act: -0.1700
Data Index: 730232 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5000. Min Range: -3.5000
Max Act: 3.1704. Min Act: -0.1700
Data Index: 4220756 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19