Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2249 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.7545. Min Act: -0.1700
Data Index: 1491959 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.5358. Min Act: -0.1700
Data Index: 8678005 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.4733. Min Act: -0.1700
Data Index: 8050880 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.4420. Min Act: -0.1700
Data Index: 1700402 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.4108. Min Act: -0.1700
Data Index: 7189842 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.3795. Min Act: -0.1700
Data Index: 856906 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.3795. Min Act: -0.1700
Data Index: 8714779 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.3483. Min Act: -0.1700
Data Index: 6600182 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.3483. Min Act: -0.1700
Data Index: 5368538 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.3483. Min Act: -0.1700
Data Index: 4887818 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.3483. Min Act: -0.1700
Data Index: 3221608 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.3483. Min Act: -0.1700
Data Index: 3370192 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.3170. Min Act: -0.1700
Data Index: 4710493 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.3170. Min Act: -0.1700
Data Index: 7729858 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.2545. Min Act: -0.1700
Data Index: 6171357 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.2858. Min Act: -0.1700
Data Index: 8024174 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.2858. Min Act: -0.1700
Data Index: 7956540 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.2858. Min Act: -0.1700
Data Index: 4346459 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.3170. Min Act: -0.1700
Data Index: 1987366 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7545. Min Range: -5.7545
Max Act: 5.2545. Min Act: -0.1700
Data Index: 5362800 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19