Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.4487. Min Act: -0.1700
Data Index: 2426156 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.3862. Min Act: -0.1700
Data Index: 4490258 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.3862. Min Act: -0.1700
Data Index: 4563558 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.3550. Min Act: -0.1700
Data Index: 722198 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.3550. Min Act: -0.1700
Data Index: 7780912 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.3550. Min Act: -0.1700
Data Index: 4178697 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.3237. Min Act: -0.1700
Data Index: 8060540 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.3237. Min Act: -0.1700
Data Index: 4662871 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.3237. Min Act: -0.1700
Data Index: 5347539 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.2925. Min Act: -0.1700
Data Index: 7142138 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.2612. Min Act: -0.1700
Data Index: 1551206 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.2925. Min Act: -0.1700
Data Index: 658119 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.2925. Min Act: -0.1700
Data Index: 2640745 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.2925. Min Act: -0.1700
Data Index: 6465568 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.2300. Min Act: -0.1700
Data Index: 6628561 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.2300. Min Act: -0.1700
Data Index: 1251109 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.2300. Min Act: -0.1700
Data Index: 7686260 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.2300. Min Act: -0.1700
Data Index: 3957096 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.1987. Min Act: -0.1700
Data Index: 4906438 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.1987. Min Act: -0.1700
Data Index: 6434665 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19