Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3129 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0492. Min Range: -6.0492
Max Act: 6.0492. Min Act: -0.1700
Data Index: 7347474 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0492. Min Range: -6.0492
Max Act: 6.0180. Min Act: -0.1700
Data Index: 2505554 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.9555. Min Act: -0.1700
Data Index: 3125795 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.9555. Min Act: -0.1700
Data Index: 7955046 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.9555. Min Act: -0.1700
Data Index: 382919 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8930. Min Act: -0.1700
Data Index: 4336781 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8305. Min Act: -0.1700
Data Index: 5893609 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8305. Min Act: -0.1700
Data Index: 4304061 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8305. Min Act: -0.1700
Data Index: 6433147 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7992. Min Act: -0.1700
Data Index: 5953337 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7992. Min Act: -0.1700
Data Index: 6883016 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7992. Min Act: -0.1700
Data Index: 1275397 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7992. Min Act: -0.1700
Data Index: 2601979 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8305. Min Act: -0.1700
Data Index: 1325055 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7992. Min Act: -0.1700
Data Index: 1169375 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7992. Min Act: -0.1700
Data Index: 5199114 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7680. Min Act: -0.1700
Data Index: 3700153 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7680. Min Act: -0.1700
Data Index: 2133770 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7367. Min Act: -0.1700
Data Index: 5709551 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7367. Min Act: -0.1700
Data Index: 6698275 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19