Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2440. Min Range: -11.2440
Max Act: 11.2440. Min Act: -0.1700
Data Index: 947463 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2440. Min Range: -11.2440
Max Act: 11.1190. Min Act: -0.1700
Data Index: 7185859 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2440. Min Range: -11.2440
Max Act: 11.0565. Min Act: -0.1700
Data Index: 3078046 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.8065. Min Act: -0.1700
Data Index: 4973320 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.7440. Min Act: -0.1700
Data Index: 8688322 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.7440. Min Act: -0.1700
Data Index: 7100880 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.6815. Min Act: -0.1700
Data Index: 751016 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.4315. Min Act: -0.1700
Data Index: 3460142 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.4315. Min Act: -0.1700
Data Index: 5953079 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.3065. Min Act: -0.1700
Data Index: 535522 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.2440. Min Act: -0.1700
Data Index: 6870918 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.2440. Min Act: -0.1700
Data Index: 8078957 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.2440. Min Act: -0.1700
Data Index: 3550673 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.1815. Min Act: -0.1700
Data Index: 4921905 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.1190. Min Act: -0.1700
Data Index: 3765535 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.1190. Min Act: -0.1700
Data Index: 7923903 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.0565. Min Act: -0.1700
Data Index: 4071015 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.1190. Min Act: -0.1700
Data Index: 4253747 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2440. Min Range: -11.2440
Max Act: 9.9940. Min Act: -0.1700
Data Index: 8155517 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2440. Min Range: -11.2440
Max Act: 10.0565. Min Act: -0.1700
Data Index: 5114700 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19