Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4314 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2323. Min Range: -6.2323
Max Act: 6.2323. Min Act: -0.1700
Data Index: 1484941 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2323. Min Range: -6.2323
Max Act: 6.1386. Min Act: -0.1700
Data Index: 6201103 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2323. Min Range: -6.2323
Max Act: 6.0761. Min Act: -0.1700
Data Index: 3054893 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2323. Min Range: -6.2323
Max Act: 6.0761. Min Act: -0.1700
Data Index: 5154941 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2323. Min Range: -6.2323
Max Act: 6.0136. Min Act: -0.1700
Data Index: 3945271 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2323. Min Range: -6.2323
Max Act: 6.0136. Min Act: -0.1700
Data Index: 2181346 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2323. Min Range: -6.2323
Max Act: 6.0136. Min Act: -0.1700
Data Index: 2637987 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.9823. Min Act: -0.1700
Data Index: 1355651 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.9823. Min Act: -0.1700
Data Index: 7459958 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.9511. Min Act: -0.1700
Data Index: 6068721 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.9198. Min Act: -0.1700
Data Index: 228496 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.9511. Min Act: -0.1700
Data Index: 7811808 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.8886. Min Act: -0.1700
Data Index: 3316991 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.8886. Min Act: -0.1700
Data Index: 7730558 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.8886. Min Act: -0.1700
Data Index: 685251 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.8573. Min Act: -0.1700
Data Index: 766954 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.8573. Min Act: -0.1700
Data Index: 1859071 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.8261. Min Act: -0.1700
Data Index: 165687 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.8261. Min Act: -0.1700
Data Index: 786975 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2323. Min Range: -6.2323
Max Act: 5.8261. Min Act: -0.1700
Data Index: 1330867 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19