Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4520 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.2406. Min Act: -0.1700
Data Index: 2143265 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.1781. Min Act: -0.1700
Data Index: 8802423 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.1468. Min Act: -0.1700
Data Index: 4230169 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.1156. Min Act: -0.1700
Data Index: 77529 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.1156. Min Act: -0.1700
Data Index: 941838 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.1156. Min Act: -0.1700
Data Index: 4349563 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.1156. Min Act: -0.1700
Data Index: 6846726 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.1156. Min Act: -0.1700
Data Index: 216561 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0843. Min Act: -0.1700
Data Index: 3773136 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.1156. Min Act: -0.1700
Data Index: 5775321 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0843. Min Act: -0.1700
Data Index: 3477415 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0843. Min Act: -0.1700
Data Index: 722410 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0531. Min Act: -0.1700
Data Index: 901607 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0531. Min Act: -0.1700
Data Index: 902050 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0218. Min Act: -0.1700
Data Index: 5344636 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0531. Min Act: -0.1700
Data Index: 2777253 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0531. Min Act: -0.1700
Data Index: 5035876 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0531. Min Act: -0.1700
Data Index: 4609969 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0531. Min Act: -0.1700
Data Index: 7873523 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2406. Min Range: -5.2406
Max Act: 5.0531. Min Act: -0.1700
Data Index: 7994977 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19