Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4501 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.8691. Min Act: -0.1700
Data Index: 4179011 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.8066. Min Act: -0.1700
Data Index: 6973303 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.7441. Min Act: -0.1700
Data Index: 5239765 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.6816. Min Act: -0.1700
Data Index: 947805 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.6504. Min Act: -0.1700
Data Index: 7030372 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.6504. Min Act: -0.1700
Data Index: 1308017 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.6191. Min Act: -0.1700
Data Index: 2373991 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.5879. Min Act: -0.1700
Data Index: 6131291 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.5879. Min Act: -0.1700
Data Index: 5369110 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.5879. Min Act: -0.1700
Data Index: 8463527 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.5566. Min Act: -0.1700
Data Index: 5720995 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.5566. Min Act: -0.1700
Data Index: 3036786 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.5254. Min Act: -0.1700
Data Index: 8423055 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.5254. Min Act: -0.1700
Data Index: 8279864 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.4941. Min Act: -0.1700
Data Index: 744307 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.5254. Min Act: -0.1700
Data Index: 8139172 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.4941. Min Act: -0.1700
Data Index: 825877 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.4629. Min Act: -0.1700
Data Index: 7961731 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.4629. Min Act: -0.1700
Data Index: 5617345 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8691. Min Range: -5.8691
Max Act: 5.4629. Min Act: -0.1700
Data Index: 8265010 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19