Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.6795. Min Act: -0.1700
Data Index: 1586739 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.4607. Min Act: -0.1700
Data Index: 2447758 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.3357. Min Act: -0.1700
Data Index: 5837514 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.2420. Min Act: -0.1700
Data Index: 3670485 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.2107. Min Act: -0.1700
Data Index: 3933533 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.2107. Min Act: -0.1700
Data Index: 8344532 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.2420. Min Act: -0.1700
Data Index: 7562818 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.2107. Min Act: -0.1700
Data Index: 5965502 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.1170. Min Act: -0.1700
Data Index: 7375796 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.0857. Min Act: -0.1700
Data Index: 1255894 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.0857. Min Act: -0.1700
Data Index: 2411294 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.0857. Min Act: -0.1700
Data Index: 4524557 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.0545. Min Act: -0.1700
Data Index: 8130225 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.0545. Min Act: -0.1700
Data Index: 8312853 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.0232. Min Act: -0.1700
Data Index: 6382066 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.0232. Min Act: -0.1700
Data Index: 6907122 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.0232. Min Act: -0.1700
Data Index: 2184288 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.0232. Min Act: -0.1700
Data Index: 6804958 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.0232. Min Act: -0.1700
Data Index: 7310785 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6795. Min Range: -5.6795
Max Act: 4.9920. Min Act: -0.1700
Data Index: 7310788 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19