Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2773. Min Range: -5.2773
Max Act: 5.2773. Min Act: -0.1700
Data Index: 4339990 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2773. Min Range: -5.2773
Max Act: 5.1523. Min Act: -0.1700
Data Index: 5827386 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2773. Min Range: -5.2773
Max Act: 5.0273. Min Act: -0.1700
Data Index: 943645 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2773. Min Range: -5.2773
Max Act: 5.0586. Min Act: -0.1700
Data Index: 5044336 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2773. Min Range: -5.2773
Max Act: 5.0586. Min Act: -0.1700
Data Index: 6163193 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2773. Min Range: -5.2773
Max Act: 5.0273. Min Act: -0.1700
Data Index: 3146055 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2773. Min Range: -5.2773
Max Act: 5.0273. Min Act: -0.1700
Data Index: 3925048 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2773. Min Range: -5.2773
Max Act: 5.0273. Min Act: -0.1700
Data Index: 5555609 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2773. Min Range: -5.2773
Max Act: 4.9961. Min Act: -0.1700
Data Index: 3503392 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2773. Min Range: -5.2773
Max Act: 5.0273. Min Act: -0.1700
Data Index: 3520871 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2773. Min Range: -5.2773
Max Act: 4.9961. Min Act: -0.1700
Data Index: 4308550 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2773. Min Range: -5.2773
Max Act: 4.9961. Min Act: -0.1700
Data Index: 8317898 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2773. Min Range: -5.2773
Max Act: 4.9961. Min Act: -0.1700
Data Index: 1538516 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2773. Min Range: -5.2773
Max Act: 4.9961. Min Act: -0.1700
Data Index: 44767 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2773. Min Range: -5.2773
Max Act: 4.9648. Min Act: -0.1700
Data Index: 2709717 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2773. Min Range: -5.2773
Max Act: 4.9961. Min Act: -0.1700
Data Index: 2641668 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2773. Min Range: -5.2773
Max Act: 4.9648. Min Act: -0.1700
Data Index: 6704864 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2773. Min Range: -5.2773
Max Act: 4.9336. Min Act: -0.1700
Data Index: 6441159 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2773. Min Range: -5.2773
Max Act: 4.9648. Min Act: -0.1700
Data Index: 3231284 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2773. Min Range: -5.2773
Max Act: 4.9336. Min Act: -0.1700
Data Index: 4724385 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19