Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5966 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6626. Min Range: -6.6626
Max Act: 6.6626. Min Act: -0.1700
Data Index: 7925034 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6626. Min Range: -6.6626
Max Act: 6.6626. Min Act: -0.1700
Data Index: 289044 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6626. Min Range: -6.6626
Max Act: 6.4126. Min Act: -0.1700
Data Index: 1072094 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6626. Min Range: -6.6626
Max Act: 6.2251. Min Act: -0.1700
Data Index: 1901715 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6626. Min Range: -6.6626
Max Act: 6.1626. Min Act: -0.1700
Data Index: 99519 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6626. Min Range: -6.6626
Max Act: 6.0376. Min Act: -0.1700
Data Index: 5612679 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6626. Min Range: -6.6626
Max Act: 6.0376. Min Act: -0.1700
Data Index: 1330773 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6626. Min Range: -6.6626
Max Act: 6.0064. Min Act: -0.1700
Data Index: 6070932 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6626. Min Range: -6.6626
Max Act: 6.0064. Min Act: -0.1700
Data Index: 6888435 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6626. Min Range: -6.6626
Max Act: 5.9751. Min Act: -0.1700
Data Index: 6082671 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6626. Min Range: -6.6626
Max Act: 5.9751. Min Act: -0.1700
Data Index: 5848578 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6626. Min Range: -6.6626
Max Act: 5.9439. Min Act: -0.1700
Data Index: 1241144 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6626. Min Range: -6.6626
Max Act: 5.9439. Min Act: -0.1700
Data Index: 5151637 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6626. Min Range: -6.6626
Max Act: 5.9439. Min Act: -0.1700
Data Index: 5541506 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6626. Min Range: -6.6626
Max Act: 5.8814. Min Act: -0.1700
Data Index: 5476474 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6626. Min Range: -6.6626
Max Act: 5.8814. Min Act: -0.1700
Data Index: 1133525 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6626. Min Range: -6.6626
Max Act: 5.8501. Min Act: -0.1700
Data Index: 6833684 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6626. Min Range: -6.6626
Max Act: 5.8189. Min Act: -0.1700
Data Index: 4265844 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6626. Min Range: -6.6626
Max Act: 5.8189. Min Act: -0.1700
Data Index: 7098241 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6626. Min Range: -6.6626
Max Act: 5.8189. Min Act: -0.1700
Data Index: 7403995 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19