Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 398 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2902. Min Range: -7.2902
Max Act: 7.2902. Min Act: -0.1700
Data Index: 5732356 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.8840. Min Act: -0.1700
Data Index: 7211566 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.7590. Min Act: -0.1700
Data Index: 1752441 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.5090. Min Act: -0.1700
Data Index: 7905734 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.3840. Min Act: -0.1700
Data Index: 825747 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.3527. Min Act: -0.1700
Data Index: 4437291 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.2590. Min Act: -0.1700
Data Index: 6755839 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.2590. Min Act: -0.1700
Data Index: 3744264 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.1652. Min Act: -0.1700
Data Index: 4594599 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.1340. Min Act: -0.1700
Data Index: 7593258 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.1027. Min Act: -0.1700
Data Index: 2020680 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.0715. Min Act: -0.1700
Data Index: 6376283 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.0402. Min Act: -0.1700
Data Index: 3046518 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.0090. Min Act: -0.1700
Data Index: 6093020 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.0090. Min Act: -0.1700
Data Index: 849395 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.0090. Min Act: -0.1700
Data Index: 2804001 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2902. Min Range: -7.2902
Max Act: 6.0090. Min Act: -0.1700
Data Index: 6972519 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2902. Min Range: -7.2902
Max Act: 5.9777. Min Act: -0.1700
Data Index: 362433 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2902. Min Range: -7.2902
Max Act: 5.9465. Min Act: -0.1700
Data Index: 7281841 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2902. Min Range: -7.2902
Max Act: 5.9465. Min Act: -0.1700
Data Index: 5360411 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19