Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4687 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.6197. Min Act: -0.1700
Data Index: 1471061 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.5727. Min Act: -0.1700
Data Index: 8468792 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.5414. Min Act: -0.1700
Data Index: 4790974 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.5414. Min Act: -0.1700
Data Index: 4972962 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.5414. Min Act: -0.1700
Data Index: 8438952 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.5257. Min Act: -0.1700
Data Index: 8320693 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.5101. Min Act: -0.1700
Data Index: 1068823 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4944. Min Act: -0.1700
Data Index: 7939649 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4787. Min Act: -0.1700
Data Index: 1345241 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4787. Min Act: -0.1700
Data Index: 53918 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4787. Min Act: -0.1700
Data Index: 862256 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4631. Min Act: -0.1700
Data Index: 7062350 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4631. Min Act: -0.1700
Data Index: 1489143 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4474. Min Act: -0.1700
Data Index: 626536 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4631. Min Act: -0.1700
Data Index: 3206356 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4474. Min Act: -0.1700
Data Index: 1302354 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4317. Min Act: -0.1700
Data Index: 5804170 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4317. Min Act: -0.1700
Data Index: 1202347 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4161. Min Act: -0.1700
Data Index: 3114702 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6197. Min Range: -3.6197
Max Act: 3.4004. Min Act: -0.1700
Data Index: 8316916 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19