Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4864 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.2478. Min Act: -0.1700
Data Index: 6572253 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.2165. Min Act: -0.1700
Data Index: 6444262 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.2165. Min Act: -0.1700
Data Index: 5738407 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.1853. Min Act: -0.1700
Data Index: 5332658 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.1228. Min Act: -0.1700
Data Index: 4570915 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.1228. Min Act: -0.1700
Data Index: 5790638 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.0915. Min Act: -0.1700
Data Index: 6301 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.0915. Min Act: -0.1700
Data Index: 3874911 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.0915. Min Act: -0.1700
Data Index: 3572450 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.0603. Min Act: -0.1700
Data Index: 6190240 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.0603. Min Act: -0.1700
Data Index: 2706263 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.0603. Min Act: -0.1700
Data Index: 584121 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.0290. Min Act: -0.1700
Data Index: 5940319 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2478. Min Range: -6.2478
Max Act: 6.0290. Min Act: -0.1700
Data Index: 2010425 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2478. Min Range: -6.2478
Max Act: 5.9978. Min Act: -0.1700
Data Index: 1380696 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2478. Min Range: -6.2478
Max Act: 5.9665. Min Act: -0.1700
Data Index: 7511369 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2478. Min Range: -6.2478
Max Act: 5.9665. Min Act: -0.1700
Data Index: 7439964 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2478. Min Range: -6.2478
Max Act: 5.9040. Min Act: -0.1700
Data Index: 5750770 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2478. Min Range: -6.2478
Max Act: 5.9353. Min Act: -0.1700
Data Index: 4039616 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2478. Min Range: -6.2478
Max Act: 5.9353. Min Act: -0.1700
Data Index: 8475614 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19