Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.9570. Min Act: -0.1700
Data Index: 8707644 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.9570. Min Act: -0.1700
Data Index: 4814258 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.9258. Min Act: -0.1700
Data Index: 783812 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.8320. Min Act: -0.1700
Data Index: 3199557 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.7383. Min Act: -0.1700
Data Index: 8146089 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.6758. Min Act: -0.1700
Data Index: 4799347 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.6758. Min Act: -0.1700
Data Index: 86725 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.7070. Min Act: -0.1700
Data Index: 1939508 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.6133. Min Act: -0.1700
Data Index: 8688997 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.6133. Min Act: -0.1700
Data Index: 3211692 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.6133. Min Act: -0.1700
Data Index: 4755436 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5820. Min Act: -0.1700
Data Index: 4206108 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5820. Min Act: -0.1700
Data Index: 3095554 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5508. Min Act: -0.1700
Data Index: 3216243 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5820. Min Act: -0.1700
Data Index: 2205549 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5508. Min Act: -0.1700
Data Index: 5002856 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5508. Min Act: -0.1700
Data Index: 2162005 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5820. Min Act: -0.1700
Data Index: 8707646 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5508. Min Act: -0.1700
Data Index: 3413568 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5195. Min Act: -0.1700
Data Index: 955941 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19