Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.9875. Min Act: -0.1700
Data Index: 5043679 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.6125. Min Act: -0.1700
Data Index: 3852741 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.5500. Min Act: -0.1700
Data Index: 3485009 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.5500. Min Act: -0.1700
Data Index: 5948698 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.4250. Min Act: -0.1700
Data Index: 6036031 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.3625. Min Act: -0.1700
Data Index: 7517813 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.3000. Min Act: -0.1700
Data Index: 2355201 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.3000. Min Act: -0.1700
Data Index: 2630454 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.3000. Min Act: -0.1700
Data Index: 8326382 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.2375. Min Act: -0.1700
Data Index: 6983068 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.1125. Min Act: -0.1700
Data Index: 3817772 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.0500. Min Act: -0.1700
Data Index: 1349169 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.0500. Min Act: -0.1700
Data Index: 7781894 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.0500. Min Act: -0.1700
Data Index: 32181 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.0500. Min Act: -0.1700
Data Index: 3626966 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9875. Min Range: -9.9875
Max Act: 8.9875. Min Act: -0.1700
Data Index: 8313257 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.0500. Min Act: -0.1700
Data Index: 5106371 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9875. Min Range: -9.9875
Max Act: 8.9875. Min Act: -0.1700
Data Index: 771277 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9875. Min Range: -9.9875
Max Act: 8.9875. Min Act: -0.1700
Data Index: 8760605 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9875. Min Range: -9.9875
Max Act: 9.0500. Min Act: -0.1700
Data Index: 4359283 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19