Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3812 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.2511. Min Act: -0.1700
Data Index: 5758036 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.2197. Min Act: -0.1700
Data Index: 6138999 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.2040. Min Act: -0.1700
Data Index: 8000467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.2040. Min Act: -0.1700
Data Index: 7884582 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.2040. Min Act: -0.1700
Data Index: 6901380 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1725. Min Act: -0.1700
Data Index: 6673309 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1883. Min Act: -0.1700
Data Index: 4561139 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1725. Min Act: -0.1700
Data Index: 6421335 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1725. Min Act: -0.1700
Data Index: 7962585 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1725. Min Act: -0.1700
Data Index: 8294166 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1725. Min Act: -0.1700
Data Index: 5168986 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1725. Min Act: -0.1700
Data Index: 1389412 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1568. Min Act: -0.1700
Data Index: 1398070 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1568. Min Act: -0.1700
Data Index: 7750920 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1568. Min Act: -0.1700
Data Index: 1578908 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1410. Min Act: -0.1700
Data Index: 6844978 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1410. Min Act: -0.1700
Data Index: 5245118 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1410. Min Act: -0.1700
Data Index: 8803 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1253. Min Act: -0.1700
Data Index: 7363512 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2511. Min Range: -3.2511
Max Act: 3.1095. Min Act: -0.1700
Data Index: 1803759 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19