Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5848 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.5922. Min Act: -0.1700
Data Index: 7080023 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.4047. Min Act: -0.1700
Data Index: 892660 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.3422. Min Act: -0.1700
Data Index: 967965 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.3422. Min Act: -0.1700
Data Index: 3243763 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.2797. Min Act: -0.1700
Data Index: 6714459 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.2797. Min Act: -0.1700
Data Index: 24007 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.2172. Min Act: -0.1700
Data Index: 7978228 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.2172. Min Act: -0.1700
Data Index: 7882946 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.1547. Min Act: -0.1700
Data Index: 4716172 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.1547. Min Act: -0.1700
Data Index: 8129896 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.1547. Min Act: -0.1700
Data Index: 8009848 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.1547. Min Act: -0.1700
Data Index: 6432719 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.1547. Min Act: -0.1700
Data Index: 3270747 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.1547. Min Act: -0.1700
Data Index: 1350279 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.0922. Min Act: -0.1700
Data Index: 4906404 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.1547. Min Act: -0.1700
Data Index: 927180 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.0297. Min Act: -0.1700
Data Index: 6600484 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.0922. Min Act: -0.1700
Data Index: 1702571 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.0922. Min Act: -0.1700
Data Index: 6869503 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5922. Min Range: -7.5922
Max Act: 7.0922. Min Act: -0.1700
Data Index: 865417 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19