Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.5079. Min Act: -0.1700
Data Index: 5550986 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.4454. Min Act: -0.1700
Data Index: 5247862 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.3829. Min Act: -0.1700
Data Index: 6963317 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.3516. Min Act: -0.1700
Data Index: 4895363 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.2891. Min Act: -0.1700
Data Index: 7301750 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.3204. Min Act: -0.1700
Data Index: 2651939 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.2891. Min Act: -0.1700
Data Index: 6139839 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.2891. Min Act: -0.1700
Data Index: 8359186 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.1954. Min Act: -0.1700
Data Index: 2799816 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.1641. Min Act: -0.1700
Data Index: 4931469 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.1641. Min Act: -0.1700
Data Index: 7761053 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.1641. Min Act: -0.1700
Data Index: 3679158 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.1641. Min Act: -0.1700
Data Index: 7079930 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.1641. Min Act: -0.1700
Data Index: 195895 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.1329. Min Act: -0.1700
Data Index: 4188199 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.1329. Min Act: -0.1700
Data Index: 59437 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.1329. Min Act: -0.1700
Data Index: 3572327 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.1329. Min Act: -0.1700
Data Index: 6583556 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.1016. Min Act: -0.1700
Data Index: 2076689 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5079. Min Range: -5.5079
Max Act: 5.0704. Min Act: -0.1700
Data Index: 2692887 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19