Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.2678. Min Act: -0.1700
Data Index: 7082513 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.2364. Min Act: -0.1700
Data Index: 2152767 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.2207. Min Act: -0.1700
Data Index: 8131567 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.2364. Min Act: -0.1700
Data Index: 5259483 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.2050. Min Act: -0.1700
Data Index: 4023180 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1892. Min Act: -0.1700
Data Index: 6182731 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1892. Min Act: -0.1700
Data Index: 2068771 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1892. Min Act: -0.1700
Data Index: 5390213 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1735. Min Act: -0.1700
Data Index: 4490560 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1892. Min Act: -0.1700
Data Index: 8328521 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1578. Min Act: -0.1700
Data Index: 152047 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1578. Min Act: -0.1700
Data Index: 3458804 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1578. Min Act: -0.1700
Data Index: 7927321 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1578. Min Act: -0.1700
Data Index: 4993042 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1420. Min Act: -0.1700
Data Index: 3583933 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1578. Min Act: -0.1700
Data Index: 823281 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1578. Min Act: -0.1700
Data Index: 7844988 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1420. Min Act: -0.1700
Data Index: 2164414 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1263. Min Act: -0.1700
Data Index: 4814736 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1578. Min Act: -0.1700
Data Index: 1871951 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19