Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.6648. Min Act: -0.1700
Data Index: 8713048 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.6335. Min Act: -0.1700
Data Index: 3725706 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.5396. Min Act: -0.1700
Data Index: 1038310 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.5396. Min Act: -0.1700
Data Index: 1122573 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.5083. Min Act: -0.1700
Data Index: 2665109 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.4769. Min Act: -0.1700
Data Index: 4930506 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.4299. Min Act: -0.1700
Data Index: 7808460 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.4142. Min Act: -0.1700
Data Index: 3943174 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.4142. Min Act: -0.1700
Data Index: 5964956 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.4299. Min Act: -0.1700
Data Index: 23674 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.3986. Min Act: -0.1700
Data Index: 5675773 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.3829. Min Act: -0.1700
Data Index: 8570442 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.3986. Min Act: -0.1700
Data Index: 7863483 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.3672. Min Act: -0.1700
Data Index: 6835091 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.3829. Min Act: -0.1700
Data Index: 6268984 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.3829. Min Act: -0.1700
Data Index: 7521370 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.3672. Min Act: -0.1700
Data Index: 3007925 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.3515. Min Act: -0.1700
Data Index: 4987704 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.3515. Min Act: -0.1700
Data Index: 1270011 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6648. Min Range: -3.6648
Max Act: 3.3515. Min Act: -0.1700
Data Index: 4731573 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19