Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2956 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.6809. Min Act: -0.1700
Data Index: 1756724 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.5559. Min Act: -0.1700
Data Index: 5621172 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.5246. Min Act: -0.1700
Data Index: 8791138 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4934. Min Act: -0.1700
Data Index: 8462410 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.5246. Min Act: -0.1700
Data Index: 7788925 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4934. Min Act: -0.1700
Data Index: 4522600 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4934. Min Act: -0.1700
Data Index: 741395 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4934. Min Act: -0.1700
Data Index: 5106450 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4934. Min Act: -0.1700
Data Index: 3577945 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4621. Min Act: -0.1700
Data Index: 8716460 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4934. Min Act: -0.1700
Data Index: 8360570 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4621. Min Act: -0.1700
Data Index: 6804325 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4621. Min Act: -0.1700
Data Index: 5860138 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4309. Min Act: -0.1700
Data Index: 6806911 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4309. Min Act: -0.1700
Data Index: 1068924 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4309. Min Act: -0.1700
Data Index: 6702279 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4309. Min Act: -0.1700
Data Index: 3577939 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4309. Min Act: -0.1700
Data Index: 4533889 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4309. Min Act: -0.1700
Data Index: 1302670 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6809. Min Range: -4.6809
Max Act: 4.4309. Min Act: -0.1700
Data Index: 4748009 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19