Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1328. Min Range: -9.1328
Max Act: 9.1328. Min Act: -0.1700
Data Index: 4840760 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1328. Min Range: -9.1328
Max Act: 8.2578. Min Act: -0.1700
Data Index: 3794833 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1328. Min Range: -9.1328
Max Act: 8.1953. Min Act: -0.1700
Data Index: 2674557 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1328. Min Range: -9.1328
Max Act: 8.1953. Min Act: -0.1700
Data Index: 5919320 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1328. Min Range: -9.1328
Max Act: 8.1328. Min Act: -0.1700
Data Index: 6862580 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1328. Min Range: -9.1328
Max Act: 8.0703. Min Act: -0.1700
Data Index: 2853044 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1328. Min Range: -9.1328
Max Act: 8.0078. Min Act: -0.1700
Data Index: 6528904 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1328. Min Range: -9.1328
Max Act: 8.0078. Min Act: -0.1700
Data Index: 6203963 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.9453. Min Act: -0.1700
Data Index: 2226614 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.8828. Min Act: -0.1700
Data Index: 6512754 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.8203. Min Act: -0.1700
Data Index: 8818837 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.8203. Min Act: -0.1700
Data Index: 7504999 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.8828. Min Act: -0.1700
Data Index: 2644726 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.8203. Min Act: -0.1700
Data Index: 488080 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.7578. Min Act: -0.1700
Data Index: 1614079 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.7578. Min Act: -0.1700
Data Index: 6661088 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.7578. Min Act: -0.1700
Data Index: 3190731 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.7578. Min Act: -0.1700
Data Index: 8136258 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.7578. Min Act: -0.1700
Data Index: 8120318 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1328. Min Range: -9.1328
Max Act: 7.6953. Min Act: -0.1700
Data Index: 660593 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19