Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3903. Min Range: -6.3903
Max Act: 6.3903. Min Act: -0.1700
Data Index: 6129693 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3903. Min Range: -6.3903
Max Act: 6.0466. Min Act: -0.1700
Data Index: 4300933 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.9841. Min Act: -0.1700
Data Index: 4374032 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.9841. Min Act: -0.1700
Data Index: 127193 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.8903. Min Act: -0.1700
Data Index: 2313956 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.7966. Min Act: -0.1700
Data Index: 8353925 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.7966. Min Act: -0.1700
Data Index: 4191867 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.8278. Min Act: -0.1700
Data Index: 1462362 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.7028. Min Act: -0.1700
Data Index: 1499664 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.7341. Min Act: -0.1700
Data Index: 6332076 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.7028. Min Act: -0.1700
Data Index: 163580 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.7028. Min Act: -0.1700
Data Index: 125879 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.7028. Min Act: -0.1700
Data Index: 7471656 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.7028. Min Act: -0.1700
Data Index: 7965478 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.6716. Min Act: -0.1700
Data Index: 7750924 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.6716. Min Act: -0.1700
Data Index: 314410 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.7028. Min Act: -0.1700
Data Index: 7754540 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.6716. Min Act: -0.1700
Data Index: 985314 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.6403. Min Act: -0.1700
Data Index: 1372470 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3903. Min Range: -6.3903
Max Act: 5.6091. Min Act: -0.1700
Data Index: 21201 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19