Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1573. Min Range: -5.1573
Max Act: 5.1573. Min Act: -0.1700
Data Index: 203763 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1573. Min Range: -5.1573
Max Act: 5.0323. Min Act: -0.1700
Data Index: 6202095 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.9698. Min Act: -0.1700
Data Index: 4219658 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.9698. Min Act: -0.1700
Data Index: 1573137 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.9386. Min Act: -0.1700
Data Index: 2202316 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.9073. Min Act: -0.1700
Data Index: 7327145 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.9073. Min Act: -0.1700
Data Index: 4307976 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.9073. Min Act: -0.1700
Data Index: 4795841 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.8448. Min Act: -0.1700
Data Index: 3829464 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.8761. Min Act: -0.1700
Data Index: 635419 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.8761. Min Act: -0.1700
Data Index: 9739 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.8448. Min Act: -0.1700
Data Index: 3528469 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.8136. Min Act: -0.1700
Data Index: 7786557 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.7511. Min Act: -0.1700
Data Index: 5949907 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.7823. Min Act: -0.1700
Data Index: 1149504 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.7823. Min Act: -0.1700
Data Index: 5244548 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.7823. Min Act: -0.1700
Data Index: 2171886 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.7511. Min Act: -0.1700
Data Index: 2248117 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.7198. Min Act: -0.1700
Data Index: 7393407 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1573. Min Range: -5.1573
Max Act: 4.7511. Min Act: -0.1700
Data Index: 5853201 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19