Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.6578. Min Act: -0.1700
Data Index: 5540789 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.5953. Min Act: -0.1700
Data Index: 8146447 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.5641. Min Act: -0.1700
Data Index: 2900907 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.5328. Min Act: -0.1700
Data Index: 3944607 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.5016. Min Act: -0.1700
Data Index: 3911907 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.5016. Min Act: -0.1700
Data Index: 5011334 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.4703. Min Act: -0.1700
Data Index: 3728792 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.5016. Min Act: -0.1700
Data Index: 2353004 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.5016. Min Act: -0.1700
Data Index: 3528675 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.4703. Min Act: -0.1700
Data Index: 1344425 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.4703. Min Act: -0.1700
Data Index: 3628208 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.4391. Min Act: -0.1700
Data Index: 8082684 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.4391. Min Act: -0.1700
Data Index: 4856963 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.3766. Min Act: -0.1700
Data Index: 1829280 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.4078. Min Act: -0.1700
Data Index: 521354 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.4078. Min Act: -0.1700
Data Index: 457596 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.4078. Min Act: -0.1700
Data Index: 8446921 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.3453. Min Act: -0.1700
Data Index: 927265 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.3453. Min Act: -0.1700
Data Index: 7809207 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6578. Min Range: -5.6578
Max Act: 5.3453. Min Act: -0.1700
Data Index: 8082685 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19