Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4352. Min Range: -6.4352
Max Act: 6.4352. Min Act: -0.1700
Data Index: 4020317 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4352. Min Range: -6.4352
Max Act: 6.1227. Min Act: -0.1700
Data Index: 8798634 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4352. Min Range: -6.4352
Max Act: 6.0602. Min Act: -0.1700
Data Index: 8198201 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.9977. Min Act: -0.1700
Data Index: 2856661 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.9664. Min Act: -0.1700
Data Index: 2542246 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.9352. Min Act: -0.1700
Data Index: 6080019 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4399012 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.9039. Min Act: -0.1700
Data Index: 3555857 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.9039. Min Act: -0.1700
Data Index: 5759712 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.9352. Min Act: -0.1700
Data Index: 2891165 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.8727. Min Act: -0.1700
Data Index: 127121 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.8727. Min Act: -0.1700
Data Index: 969981 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.8727. Min Act: -0.1700
Data Index: 7057651 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.8727. Min Act: -0.1700
Data Index: 6647536 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.8414. Min Act: -0.1700
Data Index: 5651188 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4393933 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.7477. Min Act: -0.1700
Data Index: 6678645 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.6852. Min Act: -0.1700
Data Index: 5053026 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.6852. Min Act: -0.1700
Data Index: 7580315 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4352. Min Range: -6.4352
Max Act: 5.6539. Min Act: -0.1700
Data Index: 1809646 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19