Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2859 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2474. Min Range: -7.2474
Max Act: 7.2474. Min Act: -0.1700
Data Index: 942080 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.9662. Min Act: -0.1700
Data Index: 5197570 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.9662. Min Act: -0.1700
Data Index: 959754 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.9349. Min Act: -0.1700
Data Index: 8165016 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.9037. Min Act: -0.1700
Data Index: 7206983 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.9037. Min Act: -0.1700
Data Index: 7990259 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.9037. Min Act: -0.1700
Data Index: 8325525 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.8724. Min Act: -0.1700
Data Index: 6234951 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.8724. Min Act: -0.1700
Data Index: 7684142 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.8724. Min Act: -0.1700
Data Index: 4719186 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.8412. Min Act: -0.1700
Data Index: 628193 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.8412. Min Act: -0.1700
Data Index: 6960028 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.8412. Min Act: -0.1700
Data Index: 4302037 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.8412. Min Act: -0.1700
Data Index: 7426518 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.8412. Min Act: -0.1700
Data Index: 2005275 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.8412. Min Act: -0.1700
Data Index: 8540476 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.8412. Min Act: -0.1700
Data Index: 7877301 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.8099. Min Act: -0.1700
Data Index: 8288454 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.7787. Min Act: -0.1700
Data Index: 6755644 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2474. Min Range: -7.2474
Max Act: 6.7787. Min Act: -0.1700
Data Index: 7322375 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19