Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3773 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1160. Min Range: -6.1160
Max Act: 6.1160. Min Act: -0.1700
Data Index: 6897751 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1160. Min Range: -6.1160
Max Act: 6.0223. Min Act: -0.1700
Data Index: 6535416 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.9598. Min Act: -0.1700
Data Index: 6535415 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.9285. Min Act: -0.1700
Data Index: 4366882 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.9285. Min Act: -0.1700
Data Index: 6469595 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.9285. Min Act: -0.1700
Data Index: 5348005 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8973. Min Act: -0.1700
Data Index: 3735011 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8973. Min Act: -0.1700
Data Index: 947008 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8660. Min Act: -0.1700
Data Index: 146529 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8660. Min Act: -0.1698
Data Index: 3825347 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8348. Min Act: -0.1700
Data Index: 680869 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8973. Min Act: -0.1700
Data Index: 4216611 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8660. Min Act: -0.1700
Data Index: 5016939 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8660. Min Act: -0.1700
Data Index: 1302414 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8660. Min Act: -0.1700
Data Index: 8301607 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8348. Min Act: -0.1700
Data Index: 3168090 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8035. Min Act: -0.1700
Data Index: 1766942 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.8035. Min Act: -0.1700
Data Index: 2022582 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.7723. Min Act: -0.1700
Data Index: 1467809 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1160. Min Range: -6.1160
Max Act: 5.7723. Min Act: -0.1700
Data Index: 5444010 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19