Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 703 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1879. Min Range: -4.1879
Max Act: 4.1879. Min Act: -0.1700
Data Index: 146552 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.9378. Min Act: -0.1700
Data Index: 146551 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.8440. Min Act: -0.1700
Data Index: 4771386 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.8127. Min Act: -0.1700
Data Index: 7811517 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.7815. Min Act: -0.1700
Data Index: 1740538 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.7815. Min Act: -0.1700
Data Index: 5920765 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.7502. Min Act: -0.1700
Data Index: 7337281 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.7815. Min Act: -0.1700
Data Index: 652752 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.7502. Min Act: -0.1700
Data Index: 8027439 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.7815. Min Act: -0.1700
Data Index: 580896 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.7189. Min Act: -0.1700
Data Index: 5253167 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.7189. Min Act: -0.1700
Data Index: 1474458 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.6876. Min Act: -0.1700
Data Index: 1114208 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.7189. Min Act: -0.1700
Data Index: 5718759 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.6876. Min Act: -0.1700
Data Index: 3138194 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.6563. Min Act: -0.1700
Data Index: 2950201 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.6876. Min Act: -0.1700
Data Index: 1203219 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.6563. Min Act: -0.1700
Data Index: 2213133 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.6563. Min Act: -0.1700
Data Index: 3146596 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1879. Min Range: -4.1879
Max Act: 3.6563. Min Act: -0.1700
Data Index: 5505035 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19