Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.6936. Min Act: -0.1700
Data Index: 6219903 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.5373. Min Act: -0.1700
Data Index: 1513831 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.4436. Min Act: -0.1700
Data Index: 4861374 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.4436. Min Act: -0.1700
Data Index: 6370152 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.3498. Min Act: -0.1700
Data Index: 441313 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.2873. Min Act: -0.1700
Data Index: 271516 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.2873. Min Act: -0.1700
Data Index: 2647186 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.2561. Min Act: -0.1700
Data Index: 8144738 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.2561. Min Act: -0.1700
Data Index: 3284424 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.2248. Min Act: -0.1700
Data Index: 5394416 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.2561. Min Act: -0.1700
Data Index: 51332 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.1936. Min Act: -0.1700
Data Index: 6182595 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.1623. Min Act: -0.1700
Data Index: 4861378 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.1623. Min Act: -0.1700
Data Index: 7705816 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.1623. Min Act: -0.1700
Data Index: 3347645 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.1623. Min Act: -0.1700
Data Index: 5701150 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.1311. Min Act: -0.1700
Data Index: 1004972 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.0998. Min Act: -0.1700
Data Index: 103168 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.0998. Min Act: -0.1700
Data Index: 8655702 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6936. Min Range: -6.6936
Max Act: 6.0998. Min Act: -0.1700
Data Index: 2163000 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19