Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3145 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.7408. Min Act: -0.1700
Data Index: 1951691 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.6783. Min Act: -0.1700
Data Index: 8087058 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.6783. Min Act: -0.1700
Data Index: 745336 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.5845. Min Act: -0.1700
Data Index: 3174868 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.4908. Min Act: -0.1700
Data Index: 4187754 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.4908. Min Act: -0.1700
Data Index: 4085475 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.4908. Min Act: -0.1700
Data Index: 7071687 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.4595. Min Act: -0.1700
Data Index: 4542141 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.4595. Min Act: -0.1700
Data Index: 3755111 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.4283. Min Act: -0.1700
Data Index: 960268 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.4283. Min Act: -0.1700
Data Index: 5706281 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.3658. Min Act: -0.1700
Data Index: 2719649 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.3658. Min Act: -0.1700
Data Index: 5043750 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.3970. Min Act: -0.1700
Data Index: 898236 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.3345. Min Act: -0.1700
Data Index: 6848174 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.3658. Min Act: -0.1700
Data Index: 971919 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.3033. Min Act: -0.1700
Data Index: 982244 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.2720. Min Act: -0.1700
Data Index: 5536404 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.3033. Min Act: -0.1700
Data Index: 3972853 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7408. Min Range: -6.7408
Max Act: 6.2720. Min Act: -0.1700
Data Index: 952669 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19