Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4860 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.6452. Min Act: -0.1700
Data Index: 988998 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5808. Min Act: -0.1700
Data Index: 7085742 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5808. Min Act: -0.1700
Data Index: 1815670 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5647. Min Act: -0.1700
Data Index: 5374278 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5647. Min Act: -0.1700
Data Index: 4213910 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5486. Min Act: -0.1700
Data Index: 1503611 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5486. Min Act: -0.1700
Data Index: 2192377 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5324. Min Act: -0.1700
Data Index: 998081 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5324. Min Act: -0.1700
Data Index: 1458815 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5486. Min Act: -0.1700
Data Index: 4387931 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5162. Min Act: -0.1700
Data Index: 1855874 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5162. Min Act: -0.1700
Data Index: 603624 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5162. Min Act: -0.1700
Data Index: 5682343 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5162. Min Act: -0.1700
Data Index: 8277946 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5162. Min Act: -0.1700
Data Index: 6346357 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5000. Min Act: -0.1700
Data Index: 7966803 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5162. Min Act: -0.1700
Data Index: 6911383 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5324. Min Act: -0.1700
Data Index: 1115109 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5162. Min Act: -0.1700
Data Index: 93977 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6452. Min Range: -2.6452
Max Act: 2.5000. Min Act: -0.1700
Data Index: 5171324 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19