Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.8708. Min Act: -0.1700
Data Index: 2023759 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.7770. Min Act: -0.1700
Data Index: 7434021 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.7457. Min Act: -0.1700
Data Index: 3575343 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.7301. Min Act: -0.1700
Data Index: 2124167 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.6988. Min Act: -0.1700
Data Index: 4029304 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.6675. Min Act: -0.1700
Data Index: 6679634 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.6206. Min Act: -0.1700
Data Index: 7853724 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.6206. Min Act: -0.1700
Data Index: 1103071 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.6049. Min Act: -0.1700
Data Index: 3142180 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.6049. Min Act: -0.1700
Data Index: 689396 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.5893. Min Act: -0.1700
Data Index: 4962567 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.5736. Min Act: -0.1700
Data Index: 6041752 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.5736. Min Act: -0.1700
Data Index: 271953 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.5893. Min Act: -0.1700
Data Index: 6136926 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.5736. Min Act: -0.1700
Data Index: 969041 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.5736. Min Act: -0.1700
Data Index: 5830824 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.5736. Min Act: -0.1700
Data Index: 7502816 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.5736. Min Act: -0.1700
Data Index: 1018363 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.5736. Min Act: -0.1700
Data Index: 1642820 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8708. Min Range: -3.8708
Max Act: 3.5736. Min Act: -0.1700
Data Index: 5395762 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19