Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 721 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.2559. Min Act: -0.1700
Data Index: 3240673 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.2559. Min Act: -0.1700
Data Index: 2559294 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1930. Min Act: -0.1700
Data Index: 8117669 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1773. Min Act: -0.1700
Data Index: 4402059 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1773. Min Act: -0.1700
Data Index: 1374163 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1773. Min Act: -0.1700
Data Index: 53022 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1458. Min Act: -0.1700
Data Index: 6301647 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1773. Min Act: -0.1700
Data Index: 6680517 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1458. Min Act: -0.1700
Data Index: 6711268 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1616. Min Act: -0.1700
Data Index: 8453427 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1458. Min Act: -0.1700
Data Index: 4280358 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1301. Min Act: -0.1700
Data Index: 1375757 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1458. Min Act: -0.1700
Data Index: 2400181 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1143. Min Act: -0.1700
Data Index: 6720438 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.0670. Min Act: -0.1700
Data Index: 4297516 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.1301. Min Act: -0.1700
Data Index: 3926398 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.0828. Min Act: -0.1700
Data Index: 3100249 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.0986. Min Act: -0.1700
Data Index: 2279723 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.0986. Min Act: -0.1700
Data Index: 480432 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2559. Min Range: -3.2559
Max Act: 3.0986. Min Act: -0.1700
Data Index: 5598897 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19