Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2441 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.9158. Min Act: -0.1700
Data Index: 2814408 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.8845. Min Act: -0.1700
Data Index: 1553508 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.8376. Min Act: -0.1700
Data Index: 8219028 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.8063. Min Act: -0.1700
Data Index: 6581349 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.8063. Min Act: -0.1700
Data Index: 4534262 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.7907. Min Act: -0.1700
Data Index: 3184538 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.7751. Min Act: -0.1700
Data Index: 124326 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.7438. Min Act: -0.1700
Data Index: 2269916 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.6969. Min Act: -0.1700
Data Index: 7271989 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.7125. Min Act: -0.1700
Data Index: 4391884 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.7125. Min Act: -0.1700
Data Index: 218070 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.6969. Min Act: -0.1700
Data Index: 3991165 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.6812. Min Act: -0.1700
Data Index: 7440816 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.6499. Min Act: -0.1700
Data Index: 4211474 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.6656. Min Act: -0.1700
Data Index: 4504367 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.6812. Min Act: -0.1700
Data Index: 3473121 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.6343. Min Act: -0.1700
Data Index: 5879487 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.6499. Min Act: -0.1700
Data Index: 3652841 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.6343. Min Act: -0.1700
Data Index: 6470999 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9158. Min Range: -3.9158
Max Act: 3.6499. Min Act: -0.1700
Data Index: 3773755 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19