Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2076 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.6224. Min Act: -0.1700
Data Index: 7843619 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.5599. Min Act: -0.1700
Data Index: 3241134 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.4349. Min Act: -0.1700
Data Index: 4106812 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.4349. Min Act: -0.1700
Data Index: 85286 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.3412. Min Act: -0.1700
Data Index: 2580645 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.2787. Min Act: -0.1700
Data Index: 2618846 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.2787. Min Act: -0.1700
Data Index: 6864297 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.2474. Min Act: -0.1700
Data Index: 3241135 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.1849. Min Act: -0.1700
Data Index: 4326933 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.1849. Min Act: -0.1700
Data Index: 3752867 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.1849. Min Act: -0.1700
Data Index: 6960867 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.1224. Min Act: -0.1700
Data Index: 6183613 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.0912. Min Act: -0.1700
Data Index: 7048523 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.0912. Min Act: -0.1700
Data Index: 3699275 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.0599. Min Act: -0.1700
Data Index: 133876 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.0599. Min Act: -0.1700
Data Index: 4917869 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.0912. Min Act: -0.1700
Data Index: 2319117 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6224. Min Range: -8.6224
Max Act: 8.0287. Min Act: -0.1700
Data Index: 2699908 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6224. Min Range: -8.6224
Max Act: 7.9974. Min Act: -0.1700
Data Index: 383216 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6224. Min Range: -8.6224
Max Act: 7.9974. Min Act: -0.1700
Data Index: 581720 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19