Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1453 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.7141. Min Act: -0.1700
Data Index: 1696123 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.6829. Min Act: -0.1700
Data Index: 558082 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.5266. Min Act: -0.1700
Data Index: 5403896 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.5266. Min Act: -0.1700
Data Index: 3295507 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.4954. Min Act: -0.1700
Data Index: 7870547 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.4954. Min Act: -0.1700
Data Index: 2561092 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.4329. Min Act: -0.1700
Data Index: 1751908 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.4329. Min Act: -0.1700
Data Index: 8552481 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.4016. Min Act: -0.1700
Data Index: 4713193 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.3704. Min Act: -0.1700
Data Index: 8697430 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.3391. Min Act: -0.1700
Data Index: 4299698 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.3079. Min Act: -0.1700
Data Index: 5663388 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.3391. Min Act: -0.1700
Data Index: 6510304 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.2766. Min Act: -0.1700
Data Index: 5818452 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.2766. Min Act: -0.1700
Data Index: 1330986 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.2766. Min Act: -0.1700
Data Index: 936655 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.2766. Min Act: -0.1700
Data Index: 2896860 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.2454. Min Act: -0.1700
Data Index: 2683778 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.2454. Min Act: -0.1700
Data Index: 328108 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7141. Min Range: -5.7141
Max Act: 5.2454. Min Act: -0.1700
Data Index: 1581703 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19