Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2759 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2180. Min Range: -5.2180
Max Act: 5.2180. Min Act: -0.1700
Data Index: 7087906 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2180. Min Range: -5.2180
Max Act: 5.1867. Min Act: -0.1700
Data Index: 7675370 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2180. Min Range: -5.2180
Max Act: 5.0305. Min Act: -0.1700
Data Index: 4133159 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2180. Min Range: -5.2180
Max Act: 5.0305. Min Act: -0.1700
Data Index: 4636219 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.9992. Min Act: -0.1700
Data Index: 578270 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2180. Min Range: -5.2180
Max Act: 5.0305. Min Act: -0.1700
Data Index: 6786010 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.9680. Min Act: -0.1700
Data Index: 8631411 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.9367. Min Act: -0.1700
Data Index: 578271 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.8117. Min Act: -0.1700
Data Index: 3608339 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.7805. Min Act: -0.1700
Data Index: 5523697 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.7805. Min Act: -0.1700
Data Index: 607616 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.7805. Min Act: -0.1700
Data Index: 6385740 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.7805. Min Act: -0.1700
Data Index: 6368462 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.7492. Min Act: -0.1700
Data Index: 5143159 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.7492. Min Act: -0.1700
Data Index: 108050 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.7492. Min Act: -0.1700
Data Index: 3730996 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.7492. Min Act: -0.1700
Data Index: 73979 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.7180. Min Act: -0.1700
Data Index: 5817312 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.7492. Min Act: -0.1700
Data Index: 569417 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2180. Min Range: -5.2180
Max Act: 4.7180. Min Act: -0.1700
Data Index: 1803384 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19