Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3288 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.8502. Min Act: -0.1700
Data Index: 2575346 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.4752. Min Act: -0.1700
Data Index: 8058710 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.3502. Min Act: -0.1700
Data Index: 5625692 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.3502. Min Act: -0.1700
Data Index: 952351 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.2877. Min Act: -0.1700
Data Index: 4571321 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.2252. Min Act: -0.1700
Data Index: 6670452 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.2252. Min Act: -0.1699
Data Index: 4627626 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.1627. Min Act: -0.1699
Data Index: 4200346 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.1627. Min Act: -0.1700
Data Index: 4877144 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.1627. Min Act: -0.1700
Data Index: 290643 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.1002. Min Act: -0.1699
Data Index: 3438453 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.1002. Min Act: -0.1700
Data Index: 8568308 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.1002. Min Act: -0.1700
Data Index: 311774 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8502. Min Range: -9.8502
Max Act: 8.9752. Min Act: -0.1700
Data Index: 5971935 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.0377. Min Act: -0.1698
Data Index: 7039915 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.0377. Min Act: -0.1700
Data Index: 2144405 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.0377. Min Act: -0.1700
Data Index: 4877148 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.0377. Min Act: -0.1700
Data Index: 2031630 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8502. Min Range: -9.8502
Max Act: 9.0377. Min Act: -0.1700
Data Index: 3468735 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8502. Min Range: -9.8502
Max Act: 8.9752. Min Act: -0.1700
Data Index: 5312158 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19