Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0020. Min Range: -4.0020
Max Act: 4.0020. Min Act: -0.1700
Data Index: 6836622 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.9394. Min Act: -0.1700
Data Index: 7133439 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.9394. Min Act: -0.1700
Data Index: 4169919 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.9394. Min Act: -0.1700
Data Index: 2500041 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8769. Min Act: -0.1700
Data Index: 6509215 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8769. Min Act: -0.1700
Data Index: 1229585 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8769. Min Act: -0.1700
Data Index: 8610829 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8769. Min Act: -0.1700
Data Index: 2412046 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8769. Min Act: -0.1700
Data Index: 501490 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8456. Min Act: -0.1700
Data Index: 3522042 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8456. Min Act: -0.1700
Data Index: 6371258 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8456. Min Act: -0.1700
Data Index: 3646205 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8300. Min Act: -0.1700
Data Index: 2448726 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8300. Min Act: -0.1700
Data Index: 1147614 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8456. Min Act: -0.1700
Data Index: 145278 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8144. Min Act: -0.1700
Data Index: 4812720 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8144. Min Act: -0.1700
Data Index: 1534656 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.7987. Min Act: -0.1700
Data Index: 8197396 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.7675. Min Act: -0.1700
Data Index: 3862666 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.7518. Min Act: -0.1700
Data Index: 2364027 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19