Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1850 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3898. Min Range: -4.3898
Max Act: 4.3898. Min Act: -0.1700
Data Index: 8445079 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3898. Min Range: -4.3898
Max Act: 4.2648. Min Act: -0.1700
Data Index: 4912577 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3898. Min Range: -4.3898
Max Act: 4.2335. Min Act: -0.1700
Data Index: 6042103 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3898. Min Range: -4.3898
Max Act: 4.1710. Min Act: -0.1700
Data Index: 8616845 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3898. Min Range: -4.3898
Max Act: 4.1397. Min Act: -0.1700
Data Index: 6397177 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3898. Min Range: -4.3898
Max Act: 4.0772. Min Act: -0.1700
Data Index: 8670232 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3898. Min Range: -4.3898
Max Act: 4.0147. Min Act: -0.1700
Data Index: 7058116 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3898. Min Range: -4.3898
Max Act: 4.0147. Min Act: -0.1700
Data Index: 4456618 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.9835. Min Act: -0.1700
Data Index: 5733442 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.9835. Min Act: -0.1700
Data Index: 4816215 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.9522. Min Act: -0.1700
Data Index: 856970 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.9835. Min Act: -0.1700
Data Index: 196139 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.9209. Min Act: -0.1700
Data Index: 7717295 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.9209. Min Act: -0.1700
Data Index: 6135307 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.9209. Min Act: -0.1700
Data Index: 6500460 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.8897. Min Act: -0.1700
Data Index: 7753712 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.8897. Min Act: -0.1700
Data Index: 193278 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.8897. Min Act: -0.1700
Data Index: 752753 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.8897. Min Act: -0.1700
Data Index: 6136375 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3898. Min Range: -4.3898
Max Act: 3.8897. Min Act: -0.1700
Data Index: 5014745 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19