Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5502 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.9484. Min Act: -0.1700
Data Index: 7913261 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.8859. Min Act: -0.1700
Data Index: 4850337 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.6047. Min Act: -0.1700
Data Index: 6642630 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.6047. Min Act: -0.1700
Data Index: 1184578 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.5734. Min Act: -0.1700
Data Index: 6090724 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.5422. Min Act: -0.1700
Data Index: 4140262 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.5109. Min Act: -0.1700
Data Index: 334639 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.5109. Min Act: -0.1700
Data Index: 1462063 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.5109. Min Act: -0.1700
Data Index: 2889838 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.4484. Min Act: -0.1700
Data Index: 6159545 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.4484. Min Act: -0.1700
Data Index: 1542095 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.4484. Min Act: -0.1700
Data Index: 2464196 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.4172. Min Act: -0.1700
Data Index: 7943248 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.4172. Min Act: -0.1700
Data Index: 1245826 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.3859. Min Act: -0.1700
Data Index: 6159163 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.4172. Min Act: -0.1700
Data Index: 8155681 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.4172. Min Act: -0.1700
Data Index: 2461989 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.3859. Min Act: -0.1700
Data Index: 2114918 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.3547. Min Act: -0.1700
Data Index: 1240276 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9484. Min Range: -5.9484
Max Act: 5.3859. Min Act: -0.1700
Data Index: 6804765 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19