Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 51 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.1329. Min Act: -0.1700
Data Index: 2357097 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.1329. Min Act: -0.1682
Data Index: 7527436 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.1329. Min Act: -0.1700
Data Index: 4357656 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.1017. Min Act: -0.1700
Data Index: 609101 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.1017. Min Act: -0.1700
Data Index: 3904100 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.0392. Min Act: -0.1700
Data Index: 1852401 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.0392. Min Act: -0.1700
Data Index: 3716589 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.0392. Min Act: -0.1700
Data Index: 354171 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.0392. Min Act: -0.1697
Data Index: 7634045 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.0392. Min Act: -0.1700
Data Index: 4341400 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.0079. Min Act: -0.1699
Data Index: 5654877 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1329. Min Range: -5.1329
Max Act: 5.0079. Min Act: -0.1693
Data Index: 3902622 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1329. Min Range: -5.1329
Max Act: 4.9767. Min Act: -0.1700
Data Index: 8077450 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1329. Min Range: -5.1329
Max Act: 4.9767. Min Act: -0.1700
Data Index: 1752118 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1329. Min Range: -5.1329
Max Act: 4.9454. Min Act: -0.1700
Data Index: 4522248 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1329. Min Range: -5.1329
Max Act: 4.9767. Min Act: -0.1700
Data Index: 965352 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1329. Min Range: -5.1329
Max Act: 4.9767. Min Act: -0.1700
Data Index: 2902144 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1329. Min Range: -5.1329
Max Act: 4.9454. Min Act: -0.1698
Data Index: 6294870 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1329. Min Range: -5.1329
Max Act: 4.9767. Min Act: -0.1700
Data Index: 5874237 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1329. Min Range: -5.1329
Max Act: 4.9454. Min Act: -0.1699
Data Index: 3365249 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19