Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.6246. Min Act: -0.1700
Data Index: 8702198 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.5621. Min Act: -0.1700
Data Index: 3931333 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.5621. Min Act: -0.1700
Data Index: 1224794 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.3121. Min Act: -0.1700
Data Index: 7737566 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.3746. Min Act: -0.1700
Data Index: 2176188 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.3746. Min Act: -0.1700
Data Index: 6709737 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.3121. Min Act: -0.1700
Data Index: 706087 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.3121. Min Act: -0.1700
Data Index: 5348308 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.3121. Min Act: -0.1700
Data Index: 706074 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.2496. Min Act: -0.1700
Data Index: 8688643 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.2496. Min Act: -0.1700
Data Index: 8479023 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.2496. Min Act: -0.1700
Data Index: 6340301 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.2496. Min Act: -0.1700
Data Index: 966359 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.1871. Min Act: -0.1700
Data Index: 5715227 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.1871. Min Act: -0.1700
Data Index: 5150256 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.1871. Min Act: -0.1700
Data Index: 6822817 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.1871. Min Act: -0.1700
Data Index: 8440697 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.1246. Min Act: -0.1700
Data Index: 6659220 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.1246. Min Act: -0.1700
Data Index: 6868916 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6246. Min Range: -8.6246
Max Act: 8.1246. Min Act: -0.1700
Data Index: 4714170 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19