Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5350 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.3736. Min Act: -0.1700
Data Index: 3718972 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.2799. Min Act: -0.1700
Data Index: 4953793 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0924. Min Act: -0.1700
Data Index: 1640964 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0611. Min Act: -0.1700
Data Index: 3960423 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0299. Min Act: -0.1700
Data Index: 600427 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3736. Min Range: -7.3736
Max Act: 7.0299. Min Act: -0.1700
Data Index: 2789483 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.9986. Min Act: -0.1700
Data Index: 2540999 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.9361. Min Act: -0.1700
Data Index: 6744440 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.9361. Min Act: -0.1700
Data Index: 8497242 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.9049. Min Act: -0.1700
Data Index: 106269 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.9049. Min Act: -0.1700
Data Index: 2159219 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.8736. Min Act: -0.1700
Data Index: 1498554 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.8736. Min Act: -0.1700
Data Index: 1219318 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.8736. Min Act: -0.1700
Data Index: 6862585 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.8736. Min Act: -0.1700
Data Index: 1781053 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.8424. Min Act: -0.1700
Data Index: 1565829 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.8424. Min Act: -0.1700
Data Index: 4282953 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.8424. Min Act: -0.1700
Data Index: 12098 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.8424. Min Act: -0.1700
Data Index: 5429963 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3736. Min Range: -7.3736
Max Act: 6.8424. Min Act: -0.1700
Data Index: 2811650 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19