Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.7712. Min Act: -0.1700
Data Index: 1838545 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.7712. Min Act: -0.1700
Data Index: 7762431 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.7087. Min Act: -0.1700
Data Index: 2682715 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.6462. Min Act: -0.1700
Data Index: 7848038 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.6150. Min Act: -0.1700
Data Index: 3437225 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.5525. Min Act: -0.1700
Data Index: 6603436 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.5525. Min Act: -0.1700
Data Index: 5358283 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.5525. Min Act: -0.1700
Data Index: 849314 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.5212. Min Act: -0.1700
Data Index: 501219 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.5212. Min Act: -0.1700
Data Index: 2347879 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.5525. Min Act: -0.1700
Data Index: 7928363 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.4900. Min Act: -0.1700
Data Index: 737917 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.4587. Min Act: -0.1700
Data Index: 8770125 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.4900. Min Act: -0.1700
Data Index: 3437227 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.4900. Min Act: -0.1700
Data Index: 4453712 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.3962. Min Act: -0.1700
Data Index: 4348702 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.3962. Min Act: -0.1700
Data Index: 4794712 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.3025. Min Act: -0.1700
Data Index: 2622186 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.3025. Min Act: -0.1700
Data Index: 5692292 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7712. Min Range: -6.7712
Max Act: 6.3025. Min Act: -0.1700
Data Index: 6989904 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19