Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1070. Min Range: -6.1070
Max Act: 6.1070. Min Act: -0.1700
Data Index: 5218522 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1070. Min Range: -6.1070
Max Act: 6.0133. Min Act: -0.1700
Data Index: 225698 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.8570. Min Act: -0.1700
Data Index: 2262815 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.8570. Min Act: -0.1700
Data Index: 1050752 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.6695. Min Act: -0.1700
Data Index: 5345333 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.6695. Min Act: -0.1700
Data Index: 6012384 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.7008. Min Act: -0.1700
Data Index: 3198173 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.6695. Min Act: -0.1700
Data Index: 6582038 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.6383. Min Act: -0.1700
Data Index: 8580442 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.6695. Min Act: -0.1700
Data Index: 168722 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.6383. Min Act: -0.1700
Data Index: 5376088 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.6383. Min Act: -0.1700
Data Index: 3485034 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.6383. Min Act: -0.1700
Data Index: 1532719 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.6070. Min Act: -0.1700
Data Index: 6430430 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.5758. Min Act: -0.1700
Data Index: 4615751 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.6070. Min Act: -0.1700
Data Index: 7528594 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.5758. Min Act: -0.1700
Data Index: 6177462 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.5445. Min Act: -0.1700
Data Index: 8042313 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.5445. Min Act: -0.1700
Data Index: 192283 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1070. Min Range: -6.1070
Max Act: 5.5445. Min Act: -0.1700
Data Index: 2115572 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19