Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5378 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.4683. Min Act: -0.1700
Data Index: 8426274 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.4058. Min Act: -0.1700
Data Index: 3854060 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.2496. Min Act: -0.1700
Data Index: 8454877 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.1246. Min Act: -0.1699
Data Index: 6439562 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.0621. Min Act: -0.1700
Data Index: 3386889 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.0933. Min Act: -0.1700
Data Index: 7217671 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.0308. Min Act: -0.1700
Data Index: 3024369 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4683. Min Range: -5.4683
Max Act: 5.0308. Min Act: -0.1700
Data Index: 7832526 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.9996. Min Act: -0.1700
Data Index: 6249393 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.9996. Min Act: -0.1700
Data Index: 3024368 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.9996. Min Act: -0.1700
Data Index: 8426272 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.9996. Min Act: -0.1700
Data Index: 6778000 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.9371. Min Act: -0.1700
Data Index: 6249394 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.9058. Min Act: -0.1700
Data Index: 2024207 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.9058. Min Act: -0.1700
Data Index: 2713825 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.8746. Min Act: -0.1700
Data Index: 4268248 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.8746. Min Act: -0.1700
Data Index: 7117692 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.8746. Min Act: -0.1700
Data Index: 1075105 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.8746. Min Act: -0.1700
Data Index: 8238779 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4683. Min Range: -5.4683
Max Act: 4.8746. Min Act: -0.1700
Data Index: 397208 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19