Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1698 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8231. Min Range: -7.8231
Max Act: 7.6356. Min Act: -0.1700
Data Index: 8087407 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8231. Min Range: -7.8231
Max Act: 5.5731. Min Act: -0.1700
Data Index: 5491194 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8231. Min Range: -7.8231
Max Act: 7.1043. Min Act: -0.1700
Data Index: 1550307 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8231. Min Range: -7.8231
Max Act: 7.8231. Min Act: -0.1700
Data Index: 7249631 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8231. Min Range: -7.8231
Max Act: 7.1356. Min Act: -0.1700
Data Index: 4504751 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8231. Min Range: -7.8231
Max Act: 7.1668. Min Act: -0.1700
Data Index: 3735603 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8231. Min Range: -7.8231
Max Act: 5.5418. Min Act: -0.1700
Data Index: 4334735 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8231. Min Range: -7.8231
Max Act: 7.2293. Min Act: -0.1700
Data Index: 155719 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8231. Min Range: -7.8231
Max Act: 7.0106. Min Act: -0.1700
Data Index: 8495299 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8231. Min Range: -7.8231
Max Act: 6.4793. Min Act: -0.1700
Data Index: 7652071 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8231. Min Range: -7.8231
Max Act: 5.5418. Min Act: -0.1700
Data Index: 2011263 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8231. Min Range: -7.8231
Max Act: 6.4793. Min Act: -0.1700
Data Index: 8250760 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8231. Min Range: -7.8231
Max Act: 5.2293. Min Act: -0.1700
Data Index: 796961 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8231. Min Range: -7.8231
Max Act: 6.1356. Min Act: -0.1700
Data Index: 4968842 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8231. Min Range: -7.8231
Max Act: 6.2606. Min Act: -0.1700
Data Index: 6720626 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8231. Min Range: -7.8231
Max Act: 5.2293. Min Act: -0.1700
Data Index: 1371193 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8231. Min Range: -7.8231
Max Act: 6.8543. Min Act: -0.1700
Data Index: 8288714 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8231. Min Range: -7.8231
Max Act: 6.6043. Min Act: -0.1700
Data Index: 7109209 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8231. Min Range: -7.8231
Max Act: 7.3231. Min Act: -0.1700
Data Index: 1159123 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8231. Min Range: -7.8231
Max Act: 6.6668. Min Act: -0.1700
Data Index: 6545975 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19