Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4921 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6268. Min Range: -5.6268
Max Act: 5.6268. Min Act: -0.1700
Data Index: 1384724 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6268. Min Range: -5.6268
Max Act: 5.2205. Min Act: -0.1700
Data Index: 7983686 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6268. Min Range: -5.6268
Max Act: 5.1580. Min Act: -0.1700
Data Index: 576445 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6268. Min Range: -5.6268
Max Act: 5.0330. Min Act: -0.1700
Data Index: 8760883 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6268. Min Range: -5.6268
Max Act: 5.0643. Min Act: -0.1700
Data Index: 8161571 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6268. Min Range: -5.6268
Max Act: 5.0018. Min Act: -0.1700
Data Index: 7754867 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6268. Min Range: -5.6268
Max Act: 5.0330. Min Act: -0.1700
Data Index: 5066174 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.9705. Min Act: -0.1700
Data Index: 5875505 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.9705. Min Act: -0.1700
Data Index: 3068212 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.9080. Min Act: -0.1700
Data Index: 7238338 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.9080. Min Act: -0.1700
Data Index: 2889075 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.9080. Min Act: -0.1700
Data Index: 7883277 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.8768. Min Act: -0.1700
Data Index: 7952921 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.9080. Min Act: -0.1700
Data Index: 4781828 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.8455. Min Act: -0.1700
Data Index: 836573 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.8143. Min Act: -0.1700
Data Index: 5173040 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.7830. Min Act: -0.1700
Data Index: 3499581 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.8143. Min Act: -0.1700
Data Index: 6065863 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.7830. Min Act: -0.1700
Data Index: 1652675 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6268. Min Range: -5.6268
Max Act: 4.7830. Min Act: -0.1700
Data Index: 4146285 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19