Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5843 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0251. Min Range: -5.0251
Max Act: 5.0251. Min Act: -0.1700
Data Index: 6166242 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.9939. Min Act: -0.1700
Data Index: 6640155 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.9939. Min Act: -0.1700
Data Index: 7843324 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.9314. Min Act: -0.1700
Data Index: 4561476 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.9001. Min Act: -0.1700
Data Index: 5386856 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8689. Min Act: -0.1700
Data Index: 7565378 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8689. Min Act: -0.1700
Data Index: 32466 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8689. Min Act: -0.1700
Data Index: 7199299 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8689. Min Act: -0.1700
Data Index: 969612 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8689. Min Act: -0.1700
Data Index: 1083428 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8376. Min Act: -0.1700
Data Index: 8022968 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8064. Min Act: -0.1700
Data Index: 7168099 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8064. Min Act: -0.1700
Data Index: 5634971 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7751. Min Act: -0.1700
Data Index: 4074559 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7751. Min Act: -0.1700
Data Index: 4857949 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7751. Min Act: -0.1700
Data Index: 69833 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7439. Min Act: -0.1700
Data Index: 1339959 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7439. Min Act: -0.1700
Data Index: 1867346 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7126. Min Act: -0.1700
Data Index: 5460806 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7439. Min Act: -0.1700
Data Index: 1854640 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19