Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5081 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2546. Min Range: -4.2546
Max Act: 4.2546. Min Act: -0.1700
Data Index: 4213292 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2546. Min Range: -4.2546
Max Act: 4.1921. Min Act: -0.1700
Data Index: 4117621 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2546. Min Range: -4.2546
Max Act: 4.0671. Min Act: -0.1700
Data Index: 1495048 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2546. Min Range: -4.2546
Max Act: 4.0358. Min Act: -0.1700
Data Index: 4117620 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.9733. Min Act: -0.1700
Data Index: 905801 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.9421. Min Act: -0.1700
Data Index: 4117616 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.9421. Min Act: -0.1700
Data Index: 972318 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.9421. Min Act: -0.1700
Data Index: 3746149 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.9108. Min Act: -0.1700
Data Index: 4159557 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.8795. Min Act: -0.1700
Data Index: 7708365 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.8795. Min Act: -0.1700
Data Index: 4117609 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.9108. Min Act: -0.1700
Data Index: 1169137 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.8795. Min Act: -0.1700
Data Index: 3477354 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.8795. Min Act: -0.1700
Data Index: 6839260 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.8795. Min Act: -0.1700
Data Index: 6019152 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.8795. Min Act: -0.1700
Data Index: 4117600 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.8795. Min Act: -0.1700
Data Index: 1371277 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.8795. Min Act: -0.1700
Data Index: 7533390 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.8795. Min Act: -0.1700
Data Index: 3845320 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2546. Min Range: -4.2546
Max Act: 3.8483. Min Act: -0.1700
Data Index: 262287 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19