Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3600 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.7175. Min Act: -0.1700
Data Index: 8421082 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.6863. Min Act: -0.1700
Data Index: 8721480 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.6550. Min Act: -0.1700
Data Index: 4017314 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.5925. Min Act: -0.1700
Data Index: 4401249 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.6238. Min Act: -0.1700
Data Index: 4111158 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.5925. Min Act: -0.1700
Data Index: 7471544 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.5925. Min Act: -0.1700
Data Index: 1063074 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.5613. Min Act: -0.1700
Data Index: 5237336 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.5613. Min Act: -0.1700
Data Index: 8792432 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.5300. Min Act: -0.1700
Data Index: 1421265 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.5300. Min Act: -0.1700
Data Index: 8421083 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.5300. Min Act: -0.1700
Data Index: 8121468 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.4988. Min Act: -0.1700
Data Index: 6450685 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.4988. Min Act: -0.1700
Data Index: 2135626 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.4988. Min Act: -0.1700
Data Index: 8350566 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.4988. Min Act: -0.1700
Data Index: 6240161 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.4675. Min Act: -0.1700
Data Index: 8421081 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.4363. Min Act: -0.1700
Data Index: 1063073 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.4675. Min Act: -0.1700
Data Index: 1112605 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7175. Min Range: -5.7175
Max Act: 5.4675. Min Act: -0.1700
Data Index: 2699975 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19