Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2236 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.3592. Min Act: -0.1700
Data Index: 5625574 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.3592. Min Act: -0.1700
Data Index: 1852642 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.2342. Min Act: -0.1700
Data Index: 3968301 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.2030. Min Act: -0.1700
Data Index: 5129529 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.2030. Min Act: -0.1700
Data Index: 4541144 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.1717. Min Act: -0.1700
Data Index: 5122356 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.1405. Min Act: -0.1700
Data Index: 151603 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.1405. Min Act: -0.1700
Data Index: 7487034 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.0780. Min Act: -0.1700
Data Index: 4611668 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.0780. Min Act: -0.1699
Data Index: 4336486 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.0780. Min Act: -0.1700
Data Index: 7584248 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.0780. Min Act: -0.1700
Data Index: 2076343 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.0467. Min Act: -0.1700
Data Index: 4468565 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.0467. Min Act: -0.1700
Data Index: 1173479 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.0467. Min Act: -0.1700
Data Index: 1160923 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.0467. Min Act: -0.1700
Data Index: 7252178 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.0155. Min Act: -0.1700
Data Index: 7641374 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.9842. Min Act: -0.1700
Data Index: 5680065 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.9842. Min Act: -0.1700
Data Index: 23096 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.9842. Min Act: -0.1700
Data Index: 3755104 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19