Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.6255. Min Act: -0.1700
Data Index: 6205210 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.6255. Min Act: -0.1700
Data Index: 1209286 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.5630. Min Act: -0.1700
Data Index: 843609 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.4693. Min Act: -0.1700
Data Index: 5428708 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.4068. Min Act: -0.1700
Data Index: 7066384 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.4068. Min Act: -0.1700
Data Index: 8205490 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.4380. Min Act: -0.1700
Data Index: 4837483 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.4068. Min Act: -0.1700
Data Index: 3142149 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.3755. Min Act: -0.1700
Data Index: 4273196 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.3755. Min Act: -0.1700
Data Index: 4707337 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.3755. Min Act: -0.1700
Data Index: 3868534 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.3755. Min Act: -0.1700
Data Index: 289219 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.3755. Min Act: -0.1700
Data Index: 7456537 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.3755. Min Act: -0.1700
Data Index: 670266 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.3755. Min Act: -0.1700
Data Index: 4426878 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.3443. Min Act: -0.1700
Data Index: 8070752 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.3130. Min Act: -0.1700
Data Index: 5080384 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.3130. Min Act: -0.1700
Data Index: 1063845 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.2818. Min Act: -0.1700
Data Index: 4190631 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6255. Min Range: -5.6255
Max Act: 5.2818. Min Act: -0.1700
Data Index: 7640925 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19