Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2737 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.7006. Min Act: -0.1700
Data Index: 6261942 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.5756. Min Act: -0.1700
Data Index: 6591623 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.5444. Min Act: -0.1700
Data Index: 1613211 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.5131. Min Act: -0.1700
Data Index: 5627768 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.4819. Min Act: -0.1700
Data Index: 3034328 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.3881. Min Act: -0.1700
Data Index: 3889873 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.4194. Min Act: -0.1700
Data Index: 1428274 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.2944. Min Act: -0.1700
Data Index: 1426508 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.2944. Min Act: -0.1700
Data Index: 3707287 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.2319. Min Act: -0.1700
Data Index: 6482304 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.2319. Min Act: -0.1700
Data Index: 5958293 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.2319. Min Act: -0.1700
Data Index: 2229236 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.1694. Min Act: -0.1700
Data Index: 5642618 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.2006. Min Act: -0.1700
Data Index: 4905825 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.2006. Min Act: -0.1700
Data Index: 7154997 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.2006. Min Act: -0.1700
Data Index: 2981966 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.1694. Min Act: -0.1700
Data Index: 3871374 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.1694. Min Act: -0.1700
Data Index: 4923458 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.1694. Min Act: -0.1700
Data Index: 2329627 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7006. Min Range: -6.7006
Max Act: 6.1381. Min Act: -0.1700
Data Index: 1580077 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19