Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1272 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.5033. Min Act: -0.1700
Data Index: 6791033 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.3470. Min Act: -0.1700
Data Index: 7605293 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.2533. Min Act: -0.1700
Data Index: 7605294 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.2845. Min Act: -0.1700
Data Index: 6184902 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.1283. Min Act: -0.1700
Data Index: 3421441 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.0970. Min Act: -0.1700
Data Index: 1164680 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.1283. Min Act: -0.1700
Data Index: 5669701 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.0970. Min Act: -0.1700
Data Index: 7664665 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.0970. Min Act: -0.1700
Data Index: 1579174 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.0658. Min Act: -0.1700
Data Index: 2746460 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.0345. Min Act: -0.1700
Data Index: 8760672 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5033. Min Range: -6.5033
Max Act: 6.0033. Min Act: -0.1700
Data Index: 8365840 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5033. Min Range: -6.5033
Max Act: 5.9720. Min Act: -0.1700
Data Index: 4013303 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5033. Min Range: -6.5033
Max Act: 5.9720. Min Act: -0.1700
Data Index: 7737083 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5033. Min Range: -6.5033
Max Act: 5.9720. Min Act: -0.1700
Data Index: 6180158 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5033. Min Range: -6.5033
Max Act: 5.9408. Min Act: -0.1700
Data Index: 2160288 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5033. Min Range: -6.5033
Max Act: 5.9408. Min Act: -0.1700
Data Index: 8503518 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5033. Min Range: -6.5033
Max Act: 5.9408. Min Act: -0.1700
Data Index: 4042821 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5033. Min Range: -6.5033
Max Act: 5.9408. Min Act: -0.1700
Data Index: 5942908 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5033. Min Range: -6.5033
Max Act: 5.9095. Min Act: -0.1700
Data Index: 635060 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19