Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5416 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.7635. Min Act: -0.1700
Data Index: 2200887 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.6697. Min Act: -0.1700
Data Index: 982651 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.6697. Min Act: -0.1700
Data Index: 4419911 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.6697. Min Act: -0.1700
Data Index: 3926508 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.6072. Min Act: -0.1700
Data Index: 583913 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.6072. Min Act: -0.1700
Data Index: 4393410 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5760. Min Act: -0.1700
Data Index: 2200888 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5760. Min Act: -0.1700
Data Index: 2719936 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5760. Min Act: -0.1700
Data Index: 583915 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5760. Min Act: -0.1700
Data Index: 200708 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5760. Min Act: -0.1700
Data Index: 1542643 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.4822. Min Act: -0.1700
Data Index: 879551 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5447. Min Act: -0.1700
Data Index: 6599372 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5135. Min Act: -0.1700
Data Index: 330268 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5135. Min Act: -0.1700
Data Index: 6315348 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5135. Min Act: -0.1700
Data Index: 7870293 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5135. Min Act: -0.1700
Data Index: 4048879 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5135. Min Act: -0.1700
Data Index: 8442183 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.5135. Min Act: -0.1700
Data Index: 160497 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7635. Min Range: -5.7635
Max Act: 5.4822. Min Act: -0.1700
Data Index: 3077276 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19