Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.9744. Min Act: -0.1700
Data Index: 2343900 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.8494. Min Act: -0.1700
Data Index: 3212613 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.7869. Min Act: -0.1700
Data Index: 4902065 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.7869. Min Act: -0.1699
Data Index: 4151145 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.6619. Min Act: -0.1700
Data Index: 4503304 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.6619. Min Act: -0.1700
Data Index: 5141674 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.6619. Min Act: -0.1700
Data Index: 6886579 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.5994. Min Act: -0.1700
Data Index: 2146383 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.4119. Min Act: -0.1700
Data Index: 7914244 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.4119. Min Act: -0.1700
Data Index: 279626 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.3494. Min Act: -0.1700
Data Index: 3611442 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.3494. Min Act: -0.1700
Data Index: 2146394 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.2869. Min Act: -0.1700
Data Index: 2541285 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.2869. Min Act: -0.1700
Data Index: 6386802 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.2869. Min Act: -0.1700
Data Index: 4014876 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.2244. Min Act: -0.1700
Data Index: 8412612 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.1619. Min Act: -0.1700
Data Index: 6732656 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.1619. Min Act: -0.1700
Data Index: 1157601 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.1619. Min Act: -0.1700
Data Index: 1907677 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9744. Min Range: -9.9744
Max Act: 9.1619. Min Act: -0.1700
Data Index: 5538521 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19