Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3702 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1215. Min Range: -8.1215
Max Act: 8.1215. Min Act: -0.1700
Data Index: 6451022 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1215. Min Range: -8.1215
Max Act: 8.0903. Min Act: -0.1700
Data Index: 3511745 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.9965. Min Act: -0.1700
Data Index: 6581221 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.9028. Min Act: -0.1700
Data Index: 3063896 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.8715. Min Act: -0.1700
Data Index: 6941582 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.8403. Min Act: -0.1700
Data Index: 5534061 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.8403. Min Act: -0.1700
Data Index: 4389179 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.8090. Min Act: -0.1700
Data Index: 7852860 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.7778. Min Act: -0.1700
Data Index: 2356098 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.5903. Min Act: -0.1700
Data Index: 1677848 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.5903. Min Act: -0.1700
Data Index: 3815369 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.6215. Min Act: -0.1700
Data Index: 5606171 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.5903. Min Act: -0.1700
Data Index: 6868095 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.5278. Min Act: -0.1700
Data Index: 5643292 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.5278. Min Act: -0.1700
Data Index: 1710245 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.4965. Min Act: -0.1700
Data Index: 4927703 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.4653. Min Act: -0.1700
Data Index: 4811364 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.4340. Min Act: -0.1700
Data Index: 6661691 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.4340. Min Act: -0.1700
Data Index: 5698057 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1215. Min Range: -8.1215
Max Act: 7.4340. Min Act: -0.1700
Data Index: 3737941 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19