Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.3428. Min Range: -8.3428
Max Act: 8.3428. Min Act: -0.1700
Data Index: 114544 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3428. Min Range: -8.3428
Max Act: 8.0928. Min Act: -0.1696
Data Index: 809515 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.9053. Min Act: -0.1700
Data Index: 6398123 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3428. Min Range: -8.3428
Max Act: 5.9990. Min Act: -0.1700
Data Index: 5390875 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.1553. Min Act: -0.1700
Data Index: 6628950 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.4678. Min Act: -0.1700
Data Index: 7176804 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.4678. Min Act: -0.1700
Data Index: 6823284 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.3115. Min Act: -0.1700
Data Index: 6462498 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.2803. Min Act: -0.1697
Data Index: 3183157 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.4678. Min Act: -0.1700
Data Index: 7293508 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.3115. Min Act: -0.1700
Data Index: 8477623 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.3428. Min Act: -0.1700
Data Index: 6462500 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.2490. Min Act: -0.1700
Data Index: 860655 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.2803. Min Act: -0.1700
Data Index: 7287037 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.2178. Min Act: -0.1693
Data Index: 3459214 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.2803. Min Act: -0.1700
Data Index: 7287040 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.0928. Min Act: -0.1691
Data Index: 4987930 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.1553. Min Act: -0.1700
Data Index: 4732876 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.1553. Min Act: -0.1700
Data Index: 7287038 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3428. Min Range: -8.3428
Max Act: 7.0615. Min Act: -0.1700
Data Index: 3850244 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19