Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2550 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.3138. Min Act: -0.1700
Data Index: 5466867 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.2513. Min Act: -0.1700
Data Index: 5631396 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.2513. Min Act: -0.1700
Data Index: 7125898 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.2201. Min Act: -0.1700
Data Index: 8503321 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.1888. Min Act: -0.1700
Data Index: 1826782 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.0951. Min Act: -0.1700
Data Index: 2122003 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.0951. Min Act: -0.1700
Data Index: 2619383 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.0638. Min Act: -0.1700
Data Index: 7063450 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.0638. Min Act: -0.1700
Data Index: 4334968 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.0638. Min Act: -0.1700
Data Index: 1096893 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.0013. Min Act: -0.1700
Data Index: 7718187 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.0325. Min Act: -0.1700
Data Index: 2985323 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.0325. Min Act: -0.1700
Data Index: 878914 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3138. Min Range: -4.3138
Max Act: 3.9700. Min Act: -0.1700
Data Index: 2515606 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.0013. Min Act: -0.1700
Data Index: 2914205 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3138. Min Range: -4.3138
Max Act: 4.0013. Min Act: -0.1700
Data Index: 2917574 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3138. Min Range: -4.3138
Max Act: 3.9700. Min Act: -0.1700
Data Index: 7594361 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3138. Min Range: -4.3138
Max Act: 3.9700. Min Act: -0.1700
Data Index: 961292 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3138. Min Range: -4.3138
Max Act: 3.9700. Min Act: -0.1700
Data Index: 5841736 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3138. Min Range: -4.3138
Max Act: 3.9700. Min Act: -0.1700
Data Index: 611369 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19