Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5426 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0369. Min Range: -5.0369
Max Act: 5.0369. Min Act: -0.1700
Data Index: 4953698 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.9744. Min Act: -0.1700
Data Index: 7318368 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.8182. Min Act: -0.1700
Data Index: 745122 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.8182. Min Act: -0.1700
Data Index: 4794515 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.7557. Min Act: -0.1700
Data Index: 6718336 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.6931. Min Act: -0.1700
Data Index: 40845 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.6306. Min Act: -0.1700
Data Index: 631480 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.6306. Min Act: -0.1700
Data Index: 4346405 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.5369. Min Act: -0.1700
Data Index: 3426514 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.5369. Min Act: -0.1700
Data Index: 1993153 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.5369. Min Act: -0.1700
Data Index: 5548286 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.5056. Min Act: -0.1700
Data Index: 625521 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.5056. Min Act: -0.1700
Data Index: 6080943 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.4744. Min Act: -0.1700
Data Index: 1548740 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.4431. Min Act: -0.1700
Data Index: 4094925 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.3806. Min Act: -0.1700
Data Index: 7285952 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.4431. Min Act: -0.1700
Data Index: 3730652 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.4431. Min Act: -0.1700
Data Index: 1266958 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.4119. Min Act: -0.1700
Data Index: 3205725 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0369. Min Range: -5.0369
Max Act: 4.3806. Min Act: -0.1700
Data Index: 3050871 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19