Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1889 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0317. Min Range: -7.0317
Max Act: 7.0317. Min Act: -0.1700
Data Index: 1770522 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.6567. Min Act: -0.1700
Data Index: 980955 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.6567. Min Act: -0.1700
Data Index: 8012583 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.5942. Min Act: -0.1700
Data Index: 4676118 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.5942. Min Act: -0.1700
Data Index: 705021 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.4692. Min Act: -0.1700
Data Index: 6860222 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.4380. Min Act: -0.1700
Data Index: 969708 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.4067. Min Act: -0.1700
Data Index: 145017 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.3755. Min Act: -0.1700
Data Index: 4402891 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.3130. Min Act: -0.1700
Data Index: 3695575 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2817. Min Act: -0.1700
Data Index: 378309 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2817. Min Act: -0.1700
Data Index: 6174628 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2505. Min Act: -0.1700
Data Index: 3287585 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2817. Min Act: -0.1700
Data Index: 5189814 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2505. Min Act: -0.1700
Data Index: 422604 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2505. Min Act: -0.1700
Data Index: 7652911 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2192. Min Act: -0.1700
Data Index: 246458 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.2192. Min Act: -0.1700
Data Index: 7462348 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.1880. Min Act: -0.1700
Data Index: 8592581 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0317. Min Range: -7.0317
Max Act: 6.1567. Min Act: -0.1700
Data Index: 8358914 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19