Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4029 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.7494. Min Act: -0.1700
Data Index: 6604906 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.6557. Min Act: -0.1700
Data Index: 6605508 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.5307. Min Act: -0.1700
Data Index: 3519213 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.4057. Min Act: -0.1700
Data Index: 4950823 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.3744. Min Act: -0.1700
Data Index: 7943245 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.3744. Min Act: -0.1700
Data Index: 2040226 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.3432. Min Act: -0.1700
Data Index: 2970442 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.3432. Min Act: -0.1700
Data Index: 6408382 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.2807. Min Act: -0.1700
Data Index: 5812764 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.2494. Min Act: -0.1700
Data Index: 4376134 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.2494. Min Act: -0.1700
Data Index: 7494972 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.2494. Min Act: -0.1700
Data Index: 7120614 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.2494. Min Act: -0.1700
Data Index: 846867 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.2182. Min Act: -0.1700
Data Index: 989884 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.2182. Min Act: -0.1700
Data Index: 6883656 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.2182. Min Act: -0.1700
Data Index: 3833998 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.2182. Min Act: -0.1700
Data Index: 4931401 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.2182. Min Act: -0.1700
Data Index: 6888506 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.1869. Min Act: -0.1700
Data Index: 7398590 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7494. Min Range: -5.7494
Max Act: 5.1869. Min Act: -0.1700
Data Index: 2140011 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19