Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.9004. Min Act: -0.1700
Data Index: 3884248 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.9004. Min Act: -0.1700
Data Index: 7304113 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.9004. Min Act: -0.1700
Data Index: 4397148 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.9004. Min Act: -0.1700
Data Index: 6039302 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.8379. Min Act: -0.1700
Data Index: 4718138 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.8067. Min Act: -0.1700
Data Index: 200087 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.6504. Min Act: -0.1700
Data Index: 3784884 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.6817. Min Act: -0.1700
Data Index: 1521696 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.6817. Min Act: -0.1700
Data Index: 5470441 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.6504. Min Act: -0.1700
Data Index: 7609592 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.6192. Min Act: -0.1700
Data Index: 2493815 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.6192. Min Act: -0.1700
Data Index: 6319746 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.6504. Min Act: -0.1700
Data Index: 5000467 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.6192. Min Act: -0.1700
Data Index: 201700 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.5879. Min Act: -0.1700
Data Index: 7381902 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.5879. Min Act: -0.1700
Data Index: 357181 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.5567. Min Act: -0.1700
Data Index: 5732143 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.5879. Min Act: -0.1700
Data Index: 6525231 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.5254. Min Act: -0.1700
Data Index: 4743769 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9004. Min Range: -5.9004
Max Act: 5.5567. Min Act: -0.1700
Data Index: 2466520 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19