Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3181 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.4378. Min Act: -0.1700
Data Index: 4646705 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.4378. Min Act: -0.1700
Data Index: 2493036 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.4378. Min Act: -0.1700
Data Index: 8088782 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.4221. Min Act: -0.1700
Data Index: 5007086 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.4221. Min Act: -0.1700
Data Index: 3746662 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.4221. Min Act: -0.1700
Data Index: 5946757 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.4065. Min Act: -0.1700
Data Index: 636427 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.4065. Min Act: -0.1700
Data Index: 6245502 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.4065. Min Act: -0.1700
Data Index: 5011793 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.4065. Min Act: -0.1700
Data Index: 2583948 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.3908. Min Act: -0.1700
Data Index: 353430 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.3908. Min Act: -0.1700
Data Index: 5864102 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.3908. Min Act: -0.1700
Data Index: 1292651 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.3908. Min Act: -0.1700
Data Index: 3260425 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.3908. Min Act: -0.1700
Data Index: 7986247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.3908. Min Act: -0.1700
Data Index: 1074875 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.3908. Min Act: -0.1700
Data Index: 154867 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.3751. Min Act: -0.1700
Data Index: 1537723 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.3751. Min Act: -0.1700
Data Index: 1545826 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4378. Min Range: -3.4378
Max Act: 3.3751. Min Act: -0.1700
Data Index: 1646057 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19