Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4882 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2520. Min Range: -4.2520
Max Act: 4.2520. Min Act: -0.1700
Data Index: 4205929 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2520. Min Range: -4.2520
Max Act: 4.2207. Min Act: -0.1700
Data Index: 2163775 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9707. Min Act: -0.1700
Data Index: 1736584 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9707. Min Act: -0.1700
Data Index: 142439 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9707. Min Act: -0.1700
Data Index: 1851326 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9082. Min Act: -0.1700
Data Index: 1801372 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9394. Min Act: -0.1700
Data Index: 7192311 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9394. Min Act: -0.1700
Data Index: 1221401 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9082. Min Act: -0.1700
Data Index: 5041767 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9082. Min Act: -0.1700
Data Index: 5960523 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9082. Min Act: -0.1700
Data Index: 8820770 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9082. Min Act: -0.1700
Data Index: 1337166 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9394. Min Act: -0.1700
Data Index: 7351236 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.9082. Min Act: -0.1700
Data Index: 4258470 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.8769. Min Act: -0.1700
Data Index: 3587678 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.8769. Min Act: -0.1700
Data Index: 2372304 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.8769. Min Act: -0.1700
Data Index: 4671532 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.8769. Min Act: -0.1700
Data Index: 3721021 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.8769. Min Act: -0.1700
Data Index: 6230836 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2520. Min Range: -4.2520
Max Act: 3.8769. Min Act: -0.1700
Data Index: 3457251 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19