Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6383 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.6817. Min Act: -0.1700
Data Index: 8576524 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.5567. Min Act: -0.1700
Data Index: 7981569 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.4942. Min Act: -0.1700
Data Index: 6798252 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.4942. Min Act: -0.1700
Data Index: 1624448 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.4317. Min Act: -0.1700
Data Index: 1594509 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.4004. Min Act: -0.1700
Data Index: 5679468 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.3692. Min Act: -0.1700
Data Index: 3431174 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.3379. Min Act: -0.1700
Data Index: 8220545 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.3379. Min Act: -0.1700
Data Index: 8820031 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.3692. Min Act: -0.1700
Data Index: 8525715 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.3067. Min Act: -0.1700
Data Index: 8307490 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.3067. Min Act: -0.1700
Data Index: 1459316 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.2754. Min Act: -0.1700
Data Index: 130845 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.2442. Min Act: -0.1700
Data Index: 3523889 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.2129. Min Act: -0.1700
Data Index: 8167419 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.2129. Min Act: -0.1700
Data Index: 3291665 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.1192. Min Act: -0.1700
Data Index: 5068119 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.1504. Min Act: -0.1700
Data Index: 3032429 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.1192. Min Act: -0.1700
Data Index: 5078938 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6817. Min Range: -6.6817
Max Act: 6.0567. Min Act: -0.1700
Data Index: 3290349 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19