Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3279 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.4836. Min Act: -0.1700
Data Index: 8278365 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.4211. Min Act: -0.1700
Data Index: 7435077 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.3273. Min Act: -0.1700
Data Index: 2343768 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.3898. Min Act: -0.1700
Data Index: 4340180 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.3273. Min Act: -0.1700
Data Index: 6310570 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.3273. Min Act: -0.1700
Data Index: 7435076 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2961. Min Act: -0.1700
Data Index: 2269183 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2961. Min Act: -0.1700
Data Index: 6209028 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2648. Min Act: -0.1700
Data Index: 3452635 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2648. Min Act: -0.1700
Data Index: 7651391 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2648. Min Act: -0.1700
Data Index: 5326621 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2648. Min Act: -0.1700
Data Index: 5326629 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2336. Min Act: -0.1700
Data Index: 5221288 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2336. Min Act: -0.1700
Data Index: 6209056 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2336. Min Act: -0.1700
Data Index: 5298943 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2336. Min Act: -0.1700
Data Index: 5396807 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2336. Min Act: -0.1700
Data Index: 940201 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2336. Min Act: -0.1700
Data Index: 648809 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2336. Min Act: -0.1700
Data Index: 4416343 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4836. Min Range: -5.4836
Max Act: 5.2023. Min Act: -0.1700
Data Index: 6253879 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19