Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2852 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6094. Min Range: -8.6094
Max Act: 8.6094. Min Act: -0.1700
Data Index: 5392892 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6094. Min Range: -8.6094
Max Act: 8.5469. Min Act: -0.1700
Data Index: 5994883 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6094. Min Range: -8.6094
Max Act: 8.4844. Min Act: -0.1700
Data Index: 1688321 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6094. Min Range: -8.6094
Max Act: 8.2032. Min Act: -0.1700
Data Index: 4069857 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6094. Min Range: -8.6094
Max Act: 8.1407. Min Act: -0.1700
Data Index: 6768635 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6094. Min Range: -8.6094
Max Act: 8.1407. Min Act: -0.1700
Data Index: 7215831 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6094. Min Range: -8.6094
Max Act: 8.0782. Min Act: -0.1700
Data Index: 7308930 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.9844. Min Act: -0.1700
Data Index: 4716315 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.9844. Min Act: -0.1700
Data Index: 5300545 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.8907. Min Act: -0.1700
Data Index: 5669648 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.9219. Min Act: -0.1700
Data Index: 3300697 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.8282. Min Act: -0.1700
Data Index: 6186280 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.8282. Min Act: -0.1700
Data Index: 1573151 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.8594. Min Act: -0.1700
Data Index: 2724413 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.7032. Min Act: -0.1700
Data Index: 223244 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.6407. Min Act: -0.1700
Data Index: 4010296 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.6094. Min Act: -0.1700
Data Index: 631304 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.6094. Min Act: -0.1700
Data Index: 5957336 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.5782. Min Act: -0.1700
Data Index: 8289077 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6094. Min Range: -8.6094
Max Act: 7.5469. Min Act: -0.1700
Data Index: 3755890 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19