Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 348 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4877. Min Act: -0.1700
Data Index: 4529804 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4565. Min Act: -0.1700
Data Index: 2314152 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4252. Min Act: -0.1700
Data Index: 8724696 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4252. Min Act: -0.1700
Data Index: 6323429 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4252. Min Act: -0.1700
Data Index: 5958953 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3940. Min Act: -0.1700
Data Index: 4420865 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3940. Min Act: -0.1700
Data Index: 7214219 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3627. Min Act: -0.1700
Data Index: 4730325 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3315. Min Act: -0.1700
Data Index: 4518086 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3315. Min Act: -0.1700
Data Index: 4856794 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3627. Min Act: -0.1700
Data Index: 5662982 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3627. Min Act: -0.1700
Data Index: 7943585 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3315. Min Act: -0.1700
Data Index: 7954422 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3315. Min Act: -0.1700
Data Index: 686586 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3002. Min Act: -0.1700
Data Index: 2148024 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3002. Min Act: -0.1700
Data Index: 4666605 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3002. Min Act: -0.1700
Data Index: 4629892 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3002. Min Act: -0.1700
Data Index: 187837 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.2377. Min Act: -0.1700
Data Index: 735728 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.2690. Min Act: -0.1700
Data Index: 7856517 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19