Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4957 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.3375. Min Act: -0.1700
Data Index: 1763099 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.3375. Min Act: -0.1700
Data Index: 6694682 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.1500. Min Act: -0.1700
Data Index: 3595124 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.1500. Min Act: -0.1700
Data Index: 6694688 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.1187. Min Act: -0.1700
Data Index: 7943316 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.0875. Min Act: -0.1700
Data Index: 4074852 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.0875. Min Act: -0.1700
Data Index: 3595121 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.0875. Min Act: -0.1700
Data Index: 6694709 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.0562. Min Act: -0.1700
Data Index: 6694661 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.0562. Min Act: -0.1700
Data Index: 8807922 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.0562. Min Act: -0.1700
Data Index: 6694675 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.0562. Min Act: -0.1700
Data Index: 7943313 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3375. Min Range: -5.3375
Max Act: 5.0250. Min Act: -0.1700
Data Index: 6694745 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3375. Min Range: -5.3375
Max Act: 4.9937. Min Act: -0.1700
Data Index: 783961 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3375. Min Range: -5.3375
Max Act: 4.9937. Min Act: -0.1700
Data Index: 6694660 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3375. Min Range: -5.3375
Max Act: 4.9625. Min Act: -0.1700
Data Index: 1414830 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3375. Min Range: -5.3375
Max Act: 4.9625. Min Act: -0.1700
Data Index: 6694720 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3375. Min Range: -5.3375
Max Act: 4.9625. Min Act: -0.1700
Data Index: 6694658 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3375. Min Range: -5.3375
Max Act: 4.9312. Min Act: -0.1700
Data Index: 700147 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3375. Min Range: -5.3375
Max Act: 4.9312. Min Act: -0.1700
Data Index: 6608334 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19