Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1395 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.5642. Min Act: -0.1700
Data Index: 5342623 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.5334. Min Act: -0.1700
Data Index: 6316057 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.5258. Min Act: -0.1700
Data Index: 7416196 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.5107. Min Act: -0.1700
Data Index: 4985129 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4733. Min Act: -0.1700
Data Index: 1436379 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4512. Min Act: -0.1693
Data Index: 7489259 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4512. Min Act: -0.1700
Data Index: 3444966 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4439. Min Act: -0.1700
Data Index: 7707350 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4295. Min Act: -0.1700
Data Index: 773176 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4295. Min Act: -0.1700
Data Index: 8288988 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4367. Min Act: -0.1700
Data Index: 8538084 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4295. Min Act: -0.1698
Data Index: 4396324 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4223. Min Act: -0.1700
Data Index: 7969388 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4295. Min Act: -0.1683
Data Index: 2054944 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4295. Min Act: -0.1700
Data Index: 3124510 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4151. Min Act: -0.1700
Data Index: 1637280 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4080. Min Act: -0.1673
Data Index: 8055552 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4009. Min Act: -0.1700
Data Index: 884356 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.4080. Min Act: -0.1700
Data Index: 4876995 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5642. Min Range: -0.5642
Max Act: 0.3939. Min Act: -0.1700
Data Index: 6631581 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19