Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2065. Min Range: -9.2065
Max Act: 9.2065. Min Act: -0.1700
Data Index: 5111279 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2065. Min Range: -9.2065
Max Act: 9.0190. Min Act: -0.1700
Data Index: 3586839 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.8940. Min Act: -0.1700
Data Index: 6923583 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.8940. Min Act: -0.1700
Data Index: 6203952 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.7690. Min Act: -0.1700
Data Index: 671854 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.7690. Min Act: -0.1700
Data Index: 6253277 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.7690. Min Act: -0.1700
Data Index: 8313622 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.7690. Min Act: -0.1700
Data Index: 3097484 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.7065. Min Act: -0.1700
Data Index: 6074139 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.7690. Min Act: -0.1700
Data Index: 88132 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.7065. Min Act: -0.1700
Data Index: 4237182 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.7065. Min Act: -0.1700
Data Index: 4850978 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.7065. Min Act: -0.1700
Data Index: 5733380 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.6440. Min Act: -0.1700
Data Index: 1127980 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.6440. Min Act: -0.1700
Data Index: 5149833 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.5815. Min Act: -0.1700
Data Index: 3679146 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.5815. Min Act: -0.1700
Data Index: 4870689 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.5190. Min Act: -0.1700
Data Index: 455419 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.5190. Min Act: -0.1700
Data Index: 7390310 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2065. Min Range: -9.2065
Max Act: 8.5190. Min Act: -0.1700
Data Index: 7360573 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19