Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 94 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.6147. Min Act: -0.1700
Data Index: 8528090 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.6147. Min Act: -0.1700
Data Index: 6965879 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.6147. Min Act: -0.1700
Data Index: 4435942 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5986. Min Act: -0.1700
Data Index: 1239941 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5664. Min Act: -0.1700
Data Index: 3096693 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5502. Min Act: -0.1700
Data Index: 4254915 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5502. Min Act: -0.1700
Data Index: 5393052 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5341. Min Act: -0.1700
Data Index: 8305224 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5179. Min Act: -0.1700
Data Index: 861621 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5179. Min Act: -0.1700
Data Index: 1588907 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5017. Min Act: -0.1700
Data Index: 8197303 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5179. Min Act: -0.1700
Data Index: 432900 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5179. Min Act: -0.1700
Data Index: 6889832 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5179. Min Act: -0.1700
Data Index: 1361219 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5341. Min Act: -0.1700
Data Index: 1419865 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5017. Min Act: -0.1700
Data Index: 3366303 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5341. Min Act: -0.1700
Data Index: 8598942 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5017. Min Act: -0.1700
Data Index: 4431187 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.5017. Min Act: -0.1700
Data Index: 7651271 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6147. Min Range: -2.6147
Max Act: 2.4855. Min Act: -0.1700
Data Index: 1503708 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19