Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5472 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4675. Min Range: -5.4675
Max Act: 5.4675. Min Act: -0.1700
Data Index: 7249185 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4675. Min Range: -5.4675
Max Act: 5.3425. Min Act: -0.1700
Data Index: 6055758 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4675. Min Range: -5.4675
Max Act: 5.2800. Min Act: -0.1700
Data Index: 5787111 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4675. Min Range: -5.4675
Max Act: 5.1863. Min Act: -0.1700
Data Index: 772176 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4675. Min Range: -5.4675
Max Act: 5.1863. Min Act: -0.1700
Data Index: 1118651 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4675. Min Range: -5.4675
Max Act: 5.1550. Min Act: -0.1700
Data Index: 2405136 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4675. Min Range: -5.4675
Max Act: 5.1238. Min Act: -0.1700
Data Index: 7534557 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4675. Min Range: -5.4675
Max Act: 5.0925. Min Act: -0.1700
Data Index: 508445 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4675. Min Range: -5.4675
Max Act: 5.0925. Min Act: -0.1700
Data Index: 5060517 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4675. Min Range: -5.4675
Max Act: 5.0925. Min Act: -0.1700
Data Index: 8464751 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4675. Min Range: -5.4675
Max Act: 5.0925. Min Act: -0.1700
Data Index: 4962899 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4675. Min Range: -5.4675
Max Act: 4.9988. Min Act: -0.1700
Data Index: 964433 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4675. Min Range: -5.4675
Max Act: 4.9988. Min Act: -0.1700
Data Index: 8793581 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4675. Min Range: -5.4675
Max Act: 4.9988. Min Act: -0.1700
Data Index: 7656852 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4675. Min Range: -5.4675
Max Act: 4.9988. Min Act: -0.1700
Data Index: 1112145 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4675. Min Range: -5.4675
Max Act: 4.9988. Min Act: -0.1700
Data Index: 789528 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4675. Min Range: -5.4675
Max Act: 4.9988. Min Act: -0.1700
Data Index: 1099199 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4675. Min Range: -5.4675
Max Act: 4.9675. Min Act: -0.1700
Data Index: 313930 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4675. Min Range: -5.4675
Max Act: 4.9675. Min Act: -0.1700
Data Index: 6022993 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4675. Min Range: -5.4675
Max Act: 4.9675. Min Act: -0.1700
Data Index: 7856933 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19