Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2036 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0747. Min Range: -4.0747
Max Act: 4.0747. Min Act: -0.1700
Data Index: 8504460 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0747. Min Range: -4.0747
Max Act: 4.0747. Min Act: -0.1700
Data Index: 1023358 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0747. Min Range: -4.0747
Max Act: 4.0121. Min Act: -0.1700
Data Index: 7379969 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0747. Min Range: -4.0747
Max Act: 4.0121. Min Act: -0.1700
Data Index: 6158231 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0747. Min Range: -4.0747
Max Act: 4.0121. Min Act: -0.1700
Data Index: 5726802 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.9809. Min Act: -0.1700
Data Index: 407486 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0747. Min Range: -4.0747
Max Act: 4.0121. Min Act: -0.1700
Data Index: 2480824 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.9496. Min Act: -0.1700
Data Index: 7493987 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.9496. Min Act: -0.1700
Data Index: 36559 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.9496. Min Act: -0.1700
Data Index: 5673506 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.9496. Min Act: -0.1700
Data Index: 645227 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.9496. Min Act: -0.1700
Data Index: 5177124 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.9184. Min Act: -0.1700
Data Index: 2720164 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.9184. Min Act: -0.1700
Data Index: 2601771 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.9184. Min Act: -0.1700
Data Index: 848940 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.9184. Min Act: -0.1700
Data Index: 6962475 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.8871. Min Act: -0.1700
Data Index: 727674 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.8871. Min Act: -0.1700
Data Index: 3509542 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.8871. Min Act: -0.1700
Data Index: 5161006 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0747. Min Range: -4.0747
Max Act: 3.9184. Min Act: -0.1700
Data Index: 1649729 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19