Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1660. Min Range: -6.1660
Max Act: 6.1660. Min Act: -0.1700
Data Index: 1222323 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1660. Min Range: -6.1660
Max Act: 6.0097. Min Act: -0.1700
Data Index: 3095808 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.8535. Min Act: -0.1700
Data Index: 1452379 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.8222. Min Act: -0.1700
Data Index: 1772491 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.7285. Min Act: -0.1700
Data Index: 4707101 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.7285. Min Act: -0.1700
Data Index: 276296 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.7285. Min Act: -0.1700
Data Index: 4563092 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6972. Min Act: -0.1700
Data Index: 2119187 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6972. Min Act: -0.1700
Data Index: 3614511 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6972. Min Act: -0.1700
Data Index: 8114757 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6972. Min Act: -0.1700
Data Index: 753112 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6660. Min Act: -0.1700
Data Index: 4128067 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6660. Min Act: -0.1700
Data Index: 2119188 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6347. Min Act: -0.1700
Data Index: 6633811 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6347. Min Act: -0.1700
Data Index: 7508569 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6347. Min Act: -0.1700
Data Index: 3172006 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6347. Min Act: -0.1700
Data Index: 852159 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6347. Min Act: -0.1700
Data Index: 5164623 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6347. Min Act: -0.1700
Data Index: 1326651 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1660. Min Range: -6.1660
Max Act: 5.6035. Min Act: -0.1700
Data Index: 1836728 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19