Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 842 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.9749. Min Act: -0.1700
Data Index: 991235 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.6624. Min Act: -0.1700
Data Index: 6795649 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.6624. Min Act: -0.1700
Data Index: 2718369 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.6624. Min Act: -0.1700
Data Index: 6477291 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.5687. Min Act: -0.1700
Data Index: 6696705 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.5687. Min Act: -0.1700
Data Index: 6726141 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.5687. Min Act: -0.1700
Data Index: 8547002 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.5374. Min Act: -0.1700
Data Index: 4793903 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.5374. Min Act: -0.1700
Data Index: 6101808 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.5062. Min Act: -0.1700
Data Index: 3732962 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.4749. Min Act: -0.1700
Data Index: 7167179 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.4749. Min Act: -0.1700
Data Index: 1785888 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.4437. Min Act: -0.1700
Data Index: 6628400 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.4437. Min Act: -0.1700
Data Index: 7280966 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.4437. Min Act: -0.1700
Data Index: 4961001 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.4124. Min Act: -0.1700
Data Index: 6428264 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.4124. Min Act: -0.1700
Data Index: 6653820 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.4124. Min Act: -0.1700
Data Index: 7715276 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.3499. Min Act: -0.1700
Data Index: 6039175 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9749. Min Range: -5.9749
Max Act: 5.3499. Min Act: -0.1700
Data Index: 4442565 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19