Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3866 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.7465. Min Act: -0.1700
Data Index: 553532 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.4965. Min Act: -0.1700
Data Index: 7497721 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.4652. Min Act: -0.1700
Data Index: 5972865 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.2465. Min Act: -0.1700
Data Index: 2767404 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.2152. Min Act: -0.1700
Data Index: 327793 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.2152. Min Act: -0.1700
Data Index: 1081194 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.1840. Min Act: -0.1700
Data Index: 1125862 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.1840. Min Act: -0.1700
Data Index: 8110741 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.1527. Min Act: -0.1700
Data Index: 6750624 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.1527. Min Act: -0.1700
Data Index: 5402333 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.0902. Min Act: -0.1700
Data Index: 4746250 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.1215. Min Act: -0.1700
Data Index: 5281825 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.1215. Min Act: -0.1700
Data Index: 4376348 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.1215. Min Act: -0.1700
Data Index: 5939822 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.1215. Min Act: -0.1700
Data Index: 1067143 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.0902. Min Act: -0.1700
Data Index: 5810489 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.0902. Min Act: -0.1700
Data Index: 8599598 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.0902. Min Act: -0.1700
Data Index: 3564931 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.0902. Min Act: -0.1700
Data Index: 8812154 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7465. Min Range: -5.7465
Max Act: 5.0902. Min Act: -0.1700
Data Index: 2480287 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19