Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4714 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.8303. Min Act: -0.1700
Data Index: 408313 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.7366. Min Act: -0.1700
Data Index: 408308 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.6428. Min Act: -0.1700
Data Index: 1202912 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.4553. Min Act: -0.1700
Data Index: 408315 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.3928. Min Act: -0.1700
Data Index: 408314 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.3928. Min Act: -0.1700
Data Index: 7657911 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.3303. Min Act: -0.1700
Data Index: 1943475 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.3303. Min Act: -0.1700
Data Index: 408301 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.3303. Min Act: -0.1700
Data Index: 5689948 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.2991. Min Act: -0.1700
Data Index: 1251635 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.2678. Min Act: -0.1700
Data Index: 2072021 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.2366. Min Act: -0.1700
Data Index: 1562070 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.2366. Min Act: -0.1700
Data Index: 1202903 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.2678. Min Act: -0.1700
Data Index: 408303 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.2366. Min Act: -0.1700
Data Index: 408307 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.2053. Min Act: -0.1700
Data Index: 1202910 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.2053. Min Act: -0.1700
Data Index: 7657929 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.1741. Min Act: -0.1700
Data Index: 1943497 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.2366. Min Act: -0.1700
Data Index: 408302 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8303. Min Range: -5.8303
Max Act: 5.1741. Min Act: -0.1700
Data Index: 7657917 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19