Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6013 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.8809. Min Act: -0.1700
Data Index: 2855210 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.6934. Min Act: -0.1700
Data Index: 2925522 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.6934. Min Act: -0.1700
Data Index: 2895207 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.6934. Min Act: -0.1700
Data Index: 3586109 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.6934. Min Act: -0.1700
Data Index: 1335427 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.6934. Min Act: -0.1700
Data Index: 3759147 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.6934. Min Act: -0.1700
Data Index: 4624806 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.6309. Min Act: -0.1700
Data Index: 877888 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.5059. Min Act: -0.1700
Data Index: 1185774 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.5684. Min Act: -0.1700
Data Index: 4292199 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.5684. Min Act: -0.1700
Data Index: 6160213 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.5059. Min Act: -0.1700
Data Index: 6990308 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.5059. Min Act: -0.1700
Data Index: 6684822 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.5059. Min Act: -0.1700
Data Index: 4699716 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.4434. Min Act: -0.1700
Data Index: 6699771 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.5059. Min Act: -0.1700
Data Index: 1358355 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.5059. Min Act: -0.1700
Data Index: 3241762 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.4434. Min Act: -0.1700
Data Index: 1868716 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.4434. Min Act: -0.1700
Data Index: 6526990 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8809. Min Range: -8.8809
Max Act: 8.4434. Min Act: -0.1700
Data Index: 739826 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19