Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.5783. Min Act: -0.1700
Data Index: 194635 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.4533. Min Act: -0.1700
Data Index: 5871436 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.3595. Min Act: -0.1700
Data Index: 2555249 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.3283. Min Act: -0.1700
Data Index: 7381143 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.3283. Min Act: -0.1700
Data Index: 8396870 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.2658. Min Act: -0.1700
Data Index: 7614943 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.2345. Min Act: -0.1700
Data Index: 6066479 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.2658. Min Act: -0.1699
Data Index: 6859851 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.2345. Min Act: -0.1700
Data Index: 780384 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.2345. Min Act: -0.1700
Data Index: 7048821 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.2033. Min Act: -0.1700
Data Index: 4215591 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.2033. Min Act: -0.1700
Data Index: 3756272 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.2345. Min Act: -0.1700
Data Index: 7754274 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.2033. Min Act: -0.1700
Data Index: 8376306 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.2033. Min Act: -0.1700
Data Index: 2739552 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.1720. Min Act: -0.1700
Data Index: 1945573 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.1720. Min Act: -0.1700
Data Index: 4473100 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.1720. Min Act: -0.1700
Data Index: 1438660 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.1720. Min Act: -0.1700
Data Index: 744283 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5783. Min Range: -4.5783
Max Act: 4.1408. Min Act: -0.1700
Data Index: 110042 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19