Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5776 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0577. Min Range: -3.0577
Max Act: 3.0577. Min Act: -0.1700
Data Index: 961042 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.9946. Min Act: -0.1700
Data Index: 4828264 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.9629. Min Act: -0.1700
Data Index: 7411536 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8996. Min Act: -0.1700
Data Index: 6614056 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8837. Min Act: -0.1700
Data Index: 1017750 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8837. Min Act: -0.1700
Data Index: 4850074 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8996. Min Act: -0.1700
Data Index: 7215032 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8678. Min Act: -0.1700
Data Index: 3575947 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8678. Min Act: -0.1700
Data Index: 3887973 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8361. Min Act: -0.1700
Data Index: 5469854 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8520. Min Act: -0.1700
Data Index: 2629226 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8361. Min Act: -0.1700
Data Index: 4379612 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8361. Min Act: -0.1700
Data Index: 8412497 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8361. Min Act: -0.1700
Data Index: 7562867 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8042. Min Act: -0.1700
Data Index: 5920740 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8202. Min Act: -0.1700
Data Index: 6952762 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8202. Min Act: -0.1700
Data Index: 4486433 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8042. Min Act: -0.1700
Data Index: 7140626 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8042. Min Act: -0.1700
Data Index: 6055273 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0577. Min Range: -3.0577
Max Act: 2.8042. Min Act: -0.1700
Data Index: 3619821 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19