Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5259 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.2992. Min Act: -0.1700
Data Index: 4638797 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.2055. Min Act: -0.1700
Data Index: 4362383 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.1117. Min Act: -0.1700
Data Index: 8771772 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.0492. Min Act: -0.1700
Data Index: 7092590 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9867. Min Act: -0.1700
Data Index: 8146783 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9867. Min Act: -0.1700
Data Index: 2058861 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9555. Min Act: -0.1700
Data Index: 5113802 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9555. Min Act: -0.1700
Data Index: 5622120 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9555. Min Act: -0.1700
Data Index: 7664539 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.8930. Min Act: -0.1700
Data Index: 2118830 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9242. Min Act: -0.1700
Data Index: 4472220 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.8305. Min Act: -0.1700
Data Index: 6509060 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.7992. Min Act: -0.1700
Data Index: 1802791 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.7680. Min Act: -0.1700
Data Index: 5905889 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.7680. Min Act: -0.1700
Data Index: 6405896 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.7055. Min Act: -0.1700
Data Index: 7939320 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.7367. Min Act: -0.1700
Data Index: 6131446 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.7055. Min Act: -0.1700
Data Index: 4373965 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.7055. Min Act: -0.1700
Data Index: 7384394 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.6742. Min Act: -0.1700
Data Index: 4078344 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19