Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 875 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6754. Min Range: -6.6754
Max Act: 6.6754. Min Act: -0.1200
Data Index: 3434344 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6754. Min Range: -6.6754
Max Act: 6.5816. Min Act: -0.1298
Data Index: 3434342 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6754. Min Range: -6.6754
Max Act: 6.6129. Min Act: -0.1190
Data Index: 3434318 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6754. Min Range: -6.6754
Max Act: 6.5816. Min Act: -0.0274
Data Index: 3434317 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6754. Min Range: -6.6754
Max Act: 6.3316. Min Act: -0.1700
Data Index: 6195145 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6754. Min Range: -6.6754
Max Act: 6.3316. Min Act: -0.1697
Data Index: 8669948 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6754. Min Range: -6.6754
Max Act: 6.0504. Min Act: -0.1700
Data Index: 6180206 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.9566. Min Act: -0.1700
Data Index: 4670961 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.9879. Min Act: -0.1428
Data Index: 1945774 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.9566. Min Act: -0.1700
Data Index: 7707432 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.9254. Min Act: -0.0528
Data Index: 3434343 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.8941. Min Act: -0.1700
Data Index: 8204268 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.8941. Min Act: -0.1700
Data Index: 1233278 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.8629. Min Act: -0.1699
Data Index: 799181 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.8629. Min Act: -0.1700
Data Index: 3295581 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.8629. Min Act: -0.1700
Data Index: 1233279 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.8316. Min Act: -0.1699
Data Index: 5848758 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.8004. Min Act: -0.0930
Data Index: 3434341 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.7691. Min Act: -0.1700
Data Index: 1636200 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6754. Min Range: -6.6754
Max Act: 5.8004. Min Act: -0.1700
Data Index: 6786682 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19