Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4943 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.7402. Min Act: -0.1700
Data Index: 3303866 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.7090. Min Act: -0.1700
Data Index: 2753004 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.5527. Min Act: -0.1700
Data Index: 8284126 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.5840. Min Act: -0.1700
Data Index: 2659182 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.4902. Min Act: -0.1700
Data Index: 6013933 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.4902. Min Act: -0.1700
Data Index: 820037 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.4590. Min Act: -0.1700
Data Index: 768435 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.4590. Min Act: -0.1700
Data Index: 4905456 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.4590. Min Act: -0.1700
Data Index: 4974028 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.4590. Min Act: -0.1700
Data Index: 8274852 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.4277. Min Act: -0.1700
Data Index: 5590152 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.4277. Min Act: -0.1700
Data Index: 4253923 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.3965. Min Act: -0.1700
Data Index: 660317 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.3652. Min Act: -0.1700
Data Index: 173386 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.3652. Min Act: -0.1700
Data Index: 7053324 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.3340. Min Act: -0.1700
Data Index: 6666063 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.3340. Min Act: -0.1700
Data Index: 7736881 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.3027. Min Act: -0.1700
Data Index: 4105503 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.3340. Min Act: -0.1700
Data Index: 1287709 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7402. Min Range: -5.7402
Max Act: 5.3340. Min Act: -0.1700
Data Index: 5782860 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19