Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2641 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.3400. Min Act: -0.1700
Data Index: 4151495 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.3400. Min Act: -0.1700
Data Index: 8342165 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.3088. Min Act: -0.1700
Data Index: 1494845 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.3088. Min Act: -0.1700
Data Index: 6516945 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.2775. Min Act: -0.1700
Data Index: 5974414 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.2775. Min Act: -0.1700
Data Index: 5710343 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.2775. Min Act: -0.1700
Data Index: 7901069 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.1838. Min Act: -0.1700
Data Index: 8298655 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.1838. Min Act: -0.1700
Data Index: 3231902 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.1525. Min Act: -0.1700
Data Index: 7500395 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.1525. Min Act: -0.1700
Data Index: 1754786 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.1213. Min Act: -0.1700
Data Index: 3634555 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.1213. Min Act: -0.1700
Data Index: 6100492 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.1213. Min Act: -0.1700
Data Index: 8792147 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.1213. Min Act: -0.1700
Data Index: 7004619 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.1213. Min Act: -0.1700
Data Index: 2327058 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.0900. Min Act: -0.1700
Data Index: 8428664 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.0900. Min Act: -0.1700
Data Index: 1320150 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.0900. Min Act: -0.1700
Data Index: 3536064 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3400. Min Range: -5.3400
Max Act: 5.0900. Min Act: -0.1700
Data Index: 7792961 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19