Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 712 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.7453. Min Act: -0.1700
Data Index: 2171703 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.5891. Min Act: -0.1700
Data Index: 4271332 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.4953. Min Act: -0.1700
Data Index: 4189989 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.5266. Min Act: -0.1700
Data Index: 8022851 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.4328. Min Act: -0.1700
Data Index: 6305488 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.4016. Min Act: -0.1700
Data Index: 5795830 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.3703. Min Act: -0.1700
Data Index: 663532 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.3391. Min Act: -0.1700
Data Index: 4896918 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.3078. Min Act: -0.1700
Data Index: 8191654 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.2766. Min Act: -0.1700
Data Index: 1683984 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.2766. Min Act: -0.1700
Data Index: 5904658 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.2141. Min Act: -0.1700
Data Index: 7014197 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.2141. Min Act: -0.1700
Data Index: 4372064 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.2141. Min Act: -0.1700
Data Index: 7876289 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.2141. Min Act: -0.1700
Data Index: 2628681 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 5012830 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.1516. Min Act: -0.1700
Data Index: 5641043 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.1516. Min Act: -0.1700
Data Index: 479323 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 1105714 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7453. Min Range: -5.7453
Max Act: 5.1828. Min Act: -0.1700
Data Index: 5652070 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19