Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3365 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.6505. Min Act: -0.1700
Data Index: 8084494 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.5567. Min Act: -0.1700
Data Index: 2569467 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.5567. Min Act: -0.1700
Data Index: 4433726 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.5567. Min Act: -0.1700
Data Index: 4880021 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4942. Min Act: -0.1700
Data Index: 7094534 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4942. Min Act: -0.1700
Data Index: 639507 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4942. Min Act: -0.1700
Data Index: 3220718 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4317. Min Act: -0.1700
Data Index: 7623188 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4317. Min Act: -0.1700
Data Index: 2718758 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4317. Min Act: -0.1700
Data Index: 4880020 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4317. Min Act: -0.1700
Data Index: 8598885 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4005. Min Act: -0.1700
Data Index: 1018286 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4317. Min Act: -0.1700
Data Index: 4329809 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4005. Min Act: -0.1700
Data Index: 3119876 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4005. Min Act: -0.1700
Data Index: 2569466 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4317. Min Act: -0.1700
Data Index: 6506292 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.4005. Min Act: -0.1700
Data Index: 824711 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.3692. Min Act: -0.1699
Data Index: 1231550 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.3692. Min Act: -0.1699
Data Index: 4702474 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6505. Min Range: -5.6505
Max Act: 5.3380. Min Act: -0.1700
Data Index: 389566 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19