Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3174. Min Range: -8.3174
Max Act: 8.3174. Min Act: -0.1700
Data Index: 1094228 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3174. Min Range: -8.3174
Max Act: 8.2549. Min Act: -0.1700
Data Index: 7833589 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3174. Min Range: -8.3174
Max Act: 8.2549. Min Act: -0.1700
Data Index: 8292914 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3174. Min Range: -8.3174
Max Act: 8.1299. Min Act: -0.1700
Data Index: 8036558 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3174. Min Range: -8.3174
Max Act: 8.1299. Min Act: -0.1700
Data Index: 7461086 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3174. Min Range: -8.3174
Max Act: 8.1299. Min Act: -0.1700
Data Index: 8261872 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3174. Min Range: -8.3174
Max Act: 8.0674. Min Act: -0.1700
Data Index: 1635471 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3174. Min Range: -8.3174
Max Act: 8.0674. Min Act: -0.1700
Data Index: 5719506 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3174. Min Range: -8.3174
Max Act: 8.0049. Min Act: -0.1700
Data Index: 7477808 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3174. Min Range: -8.3174
Max Act: 8.0049. Min Act: -0.1700
Data Index: 2254365 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3174. Min Range: -8.3174
Max Act: 7.9424. Min Act: -0.1700
Data Index: 3640181 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3174. Min Range: -8.3174
Max Act: 7.8799. Min Act: -0.1700
Data Index: 7242048 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3174. Min Range: -8.3174
Max Act: 7.8174. Min Act: -0.1700
Data Index: 8325997 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3174. Min Range: -8.3174
Max Act: 7.8174. Min Act: -0.1700
Data Index: 1347047 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3174. Min Range: -8.3174
Max Act: 7.8174. Min Act: -0.1700
Data Index: 1930341 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3174. Min Range: -8.3174
Max Act: 7.8174. Min Act: -0.1700
Data Index: 8028800 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3174. Min Range: -8.3174
Max Act: 7.8174. Min Act: -0.1700
Data Index: 7350678 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3174. Min Range: -8.3174
Max Act: 7.7549. Min Act: -0.1700
Data Index: 4038034 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3174. Min Range: -8.3174
Max Act: 7.8174. Min Act: -0.1700
Data Index: 8004741 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3174. Min Range: -8.3174
Max Act: 7.7549. Min Act: -0.1700
Data Index: 8007833 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19