Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4912 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.8760. Min Act: -0.1700
Data Index: 7672391 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.8134. Min Act: -0.1700
Data Index: 1649657 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.8447. Min Act: -0.1700
Data Index: 6342343 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.7822. Min Act: -0.1700
Data Index: 7656892 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.7509. Min Act: -0.1700
Data Index: 6975350 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.7196. Min Act: -0.1700
Data Index: 3845345 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.7040. Min Act: -0.1700
Data Index: 2565981 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6883. Min Act: -0.1700
Data Index: 4795337 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.7196. Min Act: -0.1700
Data Index: 7439911 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6727. Min Act: -0.1700
Data Index: 1161701 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6727. Min Act: -0.1700
Data Index: 8063968 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6727. Min Act: -0.1700
Data Index: 7065801 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6727. Min Act: -0.1700
Data Index: 1367043 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6727. Min Act: -0.1700
Data Index: 7002205 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6727. Min Act: -0.1700
Data Index: 1156153 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6570. Min Act: -0.1700
Data Index: 2201024 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6570. Min Act: -0.1700
Data Index: 1767313 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6570. Min Act: -0.1700
Data Index: 1381182 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6570. Min Act: -0.1700
Data Index: 7003661 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8760. Min Range: -3.8760
Max Act: 3.6570. Min Act: -0.1700
Data Index: 1966123 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19