Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 237 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.5431. Min Act: -0.1700
Data Index: 2480088 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.5431. Min Act: -0.1700
Data Index: 8744623 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.5119. Min Act: -0.1700
Data Index: 8370999 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.5119. Min Act: -0.1700
Data Index: 2241028 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.4181. Min Act: -0.1700
Data Index: 3065567 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.3869. Min Act: -0.1700
Data Index: 4123 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.4181. Min Act: -0.1700
Data Index: 2687927 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.3869. Min Act: -0.1700
Data Index: 295633 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.2619. Min Act: -0.1700
Data Index: 8336811 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.2931. Min Act: -0.1700
Data Index: 3224497 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.2931. Min Act: -0.1700
Data Index: 6076779 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.2619. Min Act: -0.1700
Data Index: 2476807 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.2619. Min Act: -0.1700
Data Index: 839925 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.2306. Min Act: -0.1700
Data Index: 5990785 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.1994. Min Act: -0.1700
Data Index: 5999920 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.2306. Min Act: -0.1700
Data Index: 7004456 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.2306. Min Act: -0.1700
Data Index: 1814546 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.1994. Min Act: -0.1700
Data Index: 2526117 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.1994. Min Act: -0.1700
Data Index: 7547188 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5431. Min Range: -6.5431
Max Act: 6.1994. Min Act: -0.1700
Data Index: 6273335 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19