Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2556 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0212. Min Range: -6.0212
Max Act: 6.0212. Min Act: -0.1700
Data Index: 4188551 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.6774. Min Act: -0.1700
Data Index: 8030237 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.6462. Min Act: -0.1700
Data Index: 1933663 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.6462. Min Act: -0.1700
Data Index: 7819007 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.5837. Min Act: -0.1700
Data Index: 4383206 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.4899. Min Act: -0.1700
Data Index: 4151124 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.4587. Min Act: -0.1700
Data Index: 1981210 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.4587. Min Act: -0.1700
Data Index: 4554726 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.4274. Min Act: -0.1700
Data Index: 2064571 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.4274. Min Act: -0.1700
Data Index: 6405901 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.3962. Min Act: -0.1700
Data Index: 4608580 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.3962. Min Act: -0.1700
Data Index: 3873385 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.3649. Min Act: -0.1700
Data Index: 4175417 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.3024. Min Act: -0.1700
Data Index: 946816 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.3337. Min Act: -0.1700
Data Index: 8020535 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.3024. Min Act: -0.1700
Data Index: 5672831 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.3337. Min Act: -0.1700
Data Index: 575255 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.3337. Min Act: -0.1700
Data Index: 4880224 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.3337. Min Act: -0.1700
Data Index: 8831014 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0212. Min Range: -6.0212
Max Act: 5.2712. Min Act: -0.1700
Data Index: 1107400 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19