Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 411 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3075. Min Range: -7.3075
Max Act: 7.3075. Min Act: -0.1700
Data Index: 680027 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3075. Min Range: -7.3075
Max Act: 7.2763. Min Act: -0.1700
Data Index: 4741220 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3075. Min Range: -7.3075
Max Act: 7.2138. Min Act: -0.1700
Data Index: 6627978 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.9638. Min Act: -0.1700
Data Index: 4515119 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.9638. Min Act: -0.1700
Data Index: 4487293 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.9325. Min Act: -0.1700
Data Index: 2223911 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.9325. Min Act: -0.1700
Data Index: 4230206 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.9013. Min Act: -0.1700
Data Index: 2719552 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.8388. Min Act: -0.1700
Data Index: 7663685 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.8075. Min Act: -0.1700
Data Index: 7108825 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.8075. Min Act: -0.1700
Data Index: 4822178 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.8075. Min Act: -0.1700
Data Index: 1450636 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.8075. Min Act: -0.1700
Data Index: 654420 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.8075. Min Act: -0.1700
Data Index: 6637315 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.8075. Min Act: -0.1700
Data Index: 8145273 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.8075. Min Act: -0.1700
Data Index: 4208759 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.7763. Min Act: -0.1700
Data Index: 8649056 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.7763. Min Act: -0.1700
Data Index: 4498858 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.7763. Min Act: -0.1700
Data Index: 5318114 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3075. Min Range: -7.3075
Max Act: 6.7450. Min Act: -0.1700
Data Index: 5136325 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19