Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 666 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0071. Min Range: -6.0071
Max Act: 6.0071. Min Act: -0.1700
Data Index: 1290469 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8821. Min Act: -0.1700
Data Index: 8431002 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8508. Min Act: -0.1700
Data Index: 511556 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8508. Min Act: -0.1700
Data Index: 5671084 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8508. Min Act: -0.1700
Data Index: 220386 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8196. Min Act: -0.1700
Data Index: 4937567 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.8196. Min Act: -0.1700
Data Index: 6713864 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7883. Min Act: -0.1700
Data Index: 6825577 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7883. Min Act: -0.1700
Data Index: 1472324 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7883. Min Act: -0.1700
Data Index: 1137294 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7571. Min Act: -0.1700
Data Index: 3806245 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7571. Min Act: -0.1700
Data Index: 4305818 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7258. Min Act: -0.1700
Data Index: 2211530 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.6633. Min Act: -0.1700
Data Index: 4946212 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.6946. Min Act: -0.1700
Data Index: 5962229 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.7258. Min Act: -0.1700
Data Index: 6094824 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.6633. Min Act: -0.1700
Data Index: 5631517 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.6946. Min Act: -0.1700
Data Index: 8584672 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.6946. Min Act: -0.1700
Data Index: 8458641 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0071. Min Range: -6.0071
Max Act: 5.6633. Min Act: -0.1700
Data Index: 2577192 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19