Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.4863. Min Act: -0.1700
Data Index: 3885172 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.4550. Min Act: -0.1700
Data Index: 3538337 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.3925. Min Act: -0.1700
Data Index: 5291389 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.3300. Min Act: -0.1700
Data Index: 5591733 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.2988. Min Act: -0.1700
Data Index: 4137866 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.2988. Min Act: -0.1700
Data Index: 7956881 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.2675. Min Act: -0.1700
Data Index: 5414527 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.2675. Min Act: -0.1700
Data Index: 4174808 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.2363. Min Act: -0.1700
Data Index: 7828356 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.2050. Min Act: -0.1700
Data Index: 7205558 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.2050. Min Act: -0.1700
Data Index: 6760526 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.1738. Min Act: -0.1700
Data Index: 4197783 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.1425. Min Act: -0.1700
Data Index: 8312705 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.1738. Min Act: -0.1700
Data Index: 5782304 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.2050. Min Act: -0.1700
Data Index: 4135800 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.1738. Min Act: -0.1700
Data Index: 3466655 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.1738. Min Act: -0.1700
Data Index: 511009 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.1738. Min Act: -0.1700
Data Index: 7142175 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.1738. Min Act: -0.1700
Data Index: 7152631 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4863. Min Range: -7.4863
Max Act: 7.1425. Min Act: -0.1700
Data Index: 3045281 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19