Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4256 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.9610. Min Act: -0.1700
Data Index: 664834 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.9610. Min Act: -0.1700
Data Index: 6158376 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7735. Min Act: -0.1700
Data Index: 3730109 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7423. Min Act: -0.1700
Data Index: 5424388 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7423. Min Act: -0.1700
Data Index: 4507704 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7423. Min Act: -0.1700
Data Index: 6823353 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7110. Min Act: -0.1700
Data Index: 1895616 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.6485. Min Act: -0.1700
Data Index: 6136249 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.6485. Min Act: -0.1700
Data Index: 1983326 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.6485. Min Act: -0.1700
Data Index: 1043972 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.6173. Min Act: -0.1700
Data Index: 6350717 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.6485. Min Act: -0.1700
Data Index: 7801742 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.5860. Min Act: -0.1700
Data Index: 4829726 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.5548. Min Act: -0.1700
Data Index: 3918202 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.5548. Min Act: -0.1700
Data Index: 7115523 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.5548. Min Act: -0.1700
Data Index: 7060876 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.5548. Min Act: -0.1700
Data Index: 2068177 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.5235. Min Act: -0.1700
Data Index: 8593727 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.5235. Min Act: -0.1700
Data Index: 2650936 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.4923. Min Act: -0.1700
Data Index: 642536 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19