Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 415 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3601. Min Range: -5.3601
Max Act: 5.3601. Min Act: -0.1700
Data Index: 7197516 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.9226. Min Act: -0.1700
Data Index: 5688368 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.6726. Min Act: -0.1700
Data Index: 89032 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.6101. Min Act: -0.1700
Data Index: 5903631 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.6101. Min Act: -0.1700
Data Index: 941185 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.5788. Min Act: -0.1700
Data Index: 7012980 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.5788. Min Act: -0.1700
Data Index: 5176229 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.5476. Min Act: -0.1700
Data Index: 2383034 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.5163. Min Act: -0.1700
Data Index: 7287645 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.5476. Min Act: -0.1700
Data Index: 2286055 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.4851. Min Act: -0.1700
Data Index: 575148 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.4851. Min Act: -0.1700
Data Index: 92421 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.4538. Min Act: -0.1700
Data Index: 5660342 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.4538. Min Act: -0.1700
Data Index: 4015441 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.4538. Min Act: -0.1700
Data Index: 3629606 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.4538. Min Act: -0.1700
Data Index: 2155118 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.4538. Min Act: -0.1700
Data Index: 3661541 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.4226. Min Act: -0.1700
Data Index: 7049507 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.4538. Min Act: -0.1700
Data Index: 2813543 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3601. Min Range: -5.3601
Max Act: 4.4226. Min Act: -0.1700
Data Index: 4224629 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19