Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4018 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.6147. Min Act: -0.1700
Data Index: 3730460 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.5834. Min Act: -0.1700
Data Index: 8431554 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.5834. Min Act: -0.1700
Data Index: 4140418 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.4272. Min Act: -0.1700
Data Index: 4324004 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.3959. Min Act: -0.1700
Data Index: 6990802 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.3022. Min Act: -0.1700
Data Index: 1632753 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.2084. Min Act: -0.1700
Data Index: 8431771 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.2084. Min Act: -0.1700
Data Index: 4032785 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.1772. Min Act: -0.1700
Data Index: 7450678 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.1772. Min Act: -0.1700
Data Index: 7026827 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.1772. Min Act: -0.1700
Data Index: 3724062 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.1772. Min Act: -0.1700
Data Index: 3688992 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.2084. Min Act: -0.1700
Data Index: 5127116 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.1772. Min Act: -0.1700
Data Index: 3518049 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.1147. Min Act: -0.1700
Data Index: 7631192 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.0834. Min Act: -0.1700
Data Index: 6754735 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.1147. Min Act: -0.1700
Data Index: 3114403 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.1147. Min Act: -0.1700
Data Index: 4266636 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.1147. Min Act: -0.1700
Data Index: 4781609 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6147. Min Range: -6.6147
Max Act: 6.1147. Min Act: -0.1700
Data Index: 2172041 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19