Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 39 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1224. Min Range: -6.1224
Max Act: 6.1224. Min Act: -0.1700
Data Index: 6254420 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1224. Min Range: -6.1224
Max Act: 6.0911. Min Act: -0.1700
Data Index: 8127895 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1224. Min Range: -6.1224
Max Act: 6.0286. Min Act: -0.1700
Data Index: 7140244 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1224. Min Range: -6.1224
Max Act: 6.0286. Min Act: -0.1700
Data Index: 6010675 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1224. Min Range: -6.1224
Max Act: 6.0286. Min Act: -0.1700
Data Index: 936817 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.9974. Min Act: -0.1700
Data Index: 7846819 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.9349. Min Act: -0.1700
Data Index: 271754 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.9349. Min Act: -0.1700
Data Index: 7007716 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.8724. Min Act: -0.1700
Data Index: 8533657 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.8411. Min Act: -0.1700
Data Index: 8090725 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.8411. Min Act: -0.1700
Data Index: 2647495 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.8099. Min Act: -0.1700
Data Index: 1958949 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.8099. Min Act: -0.1700
Data Index: 7140248 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.8099. Min Act: -0.1700
Data Index: 8090727 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.8099. Min Act: -0.1700
Data Index: 4288600 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.7786. Min Act: -0.1700
Data Index: 8819976 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.8099. Min Act: -0.1700
Data Index: 2190612 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.7161. Min Act: -0.1700
Data Index: 7140252 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.7161. Min Act: -0.1700
Data Index: 8297679 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1224. Min Range: -6.1224
Max Act: 5.6849. Min Act: -0.1700
Data Index: 1042475 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19