Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1697 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1652. Min Act: -0.1700
Data Index: 4947570 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1652. Min Act: -0.1700
Data Index: 8281049 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1339. Min Act: -0.1700
Data Index: 669165 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1339. Min Act: -0.1700
Data Index: 1737686 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.1027. Min Act: -0.1700
Data Index: 5317809 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0714. Min Act: -0.1700
Data Index: 4678450 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0714. Min Act: -0.1700
Data Index: 6494515 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0402. Min Act: -0.1700
Data Index: 1875412 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 5747992 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 6535958 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 5354528 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 4234182 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 6844686 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 369500 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1652. Min Range: -5.1652
Max Act: 5.0089. Min Act: -0.1700
Data Index: 7548524 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1652. Min Range: -5.1652
Max Act: 4.9777. Min Act: -0.1700
Data Index: 5215702 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1652. Min Range: -5.1652
Max Act: 4.9777. Min Act: -0.1700
Data Index: 2672903 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1652. Min Range: -5.1652
Max Act: 4.9777. Min Act: -0.1700
Data Index: 2672913 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1652. Min Range: -5.1652
Max Act: 4.9777. Min Act: -0.1700
Data Index: 645655 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1652. Min Range: -5.1652
Max Act: 4.9464. Min Act: -0.1700
Data Index: 4234181 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19