Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.5518. Min Act: -0.1700
Data Index: 881148 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.4581. Min Act: -0.1700
Data Index: 2572021 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.4268. Min Act: -0.1700
Data Index: 424375 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.3956. Min Act: -0.1700
Data Index: 5669122 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.3643. Min Act: -0.1700
Data Index: 421853 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.3643. Min Act: -0.1700
Data Index: 320328 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.3643. Min Act: -0.1700
Data Index: 984156 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.3643. Min Act: -0.1700
Data Index: 1962418 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.3331. Min Act: -0.1700
Data Index: 2307672 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.3331. Min Act: -0.1700
Data Index: 2738843 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.2706. Min Act: -0.1700
Data Index: 4453777 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.2706. Min Act: -0.1700
Data Index: 5924796 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.2706. Min Act: -0.1700
Data Index: 120394 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.2706. Min Act: -0.1700
Data Index: 2480347 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.3018. Min Act: -0.1700
Data Index: 8082541 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.2393. Min Act: -0.1700
Data Index: 1665654 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.2393. Min Act: -0.1700
Data Index: 2449889 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.2393. Min Act: -0.1700
Data Index: 1365753 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.2393. Min Act: -0.1700
Data Index: 5258336 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5518. Min Range: -4.5518
Max Act: 4.2393. Min Act: -0.1700
Data Index: 5223793 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19