Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1393. Min Range: -3.1393
Max Act: 3.1393. Min Act: -0.1700
Data Index: 6736037 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.9341. Min Act: -0.1700
Data Index: 8284687 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.9024. Min Act: -0.1700
Data Index: 3260167 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.9182. Min Act: -0.1700
Data Index: 6477373 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.8707. Min Act: -0.1700
Data Index: 2902881 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.7912. Min Act: -0.1700
Data Index: 8038391 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.7912. Min Act: -0.1700
Data Index: 4150635 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.7593. Min Act: -0.1700
Data Index: 5665649 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.7273. Min Act: -0.1700
Data Index: 975959 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.7433. Min Act: -0.1700
Data Index: 1870405 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.7273. Min Act: -0.1700
Data Index: 7739822 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.6953. Min Act: -0.1700
Data Index: 2384619 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.6953. Min Act: -0.1700
Data Index: 8348704 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.7113. Min Act: -0.1700
Data Index: 546976 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.6953. Min Act: -0.1700
Data Index: 5632308 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.7113. Min Act: -0.1700
Data Index: 5463659 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.6953. Min Act: -0.1700
Data Index: 6441892 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.6953. Min Act: -0.1700
Data Index: 5223372 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.6953. Min Act: -0.1700
Data Index: 8002698 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1393. Min Range: -3.1393
Max Act: 2.7113. Min Act: -0.1700
Data Index: 4476943 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19