Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1917 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.8388. Min Act: -0.1700
Data Index: 2174359 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.8388. Min Act: -0.1700
Data Index: 711829 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.8075. Min Act: -0.1700
Data Index: 6381605 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.7763. Min Act: -0.1700
Data Index: 231797 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.7763. Min Act: -0.1700
Data Index: 7787590 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.7450. Min Act: -0.1700
Data Index: 3606317 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.7450. Min Act: -0.1700
Data Index: 711828 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.7138. Min Act: -0.1700
Data Index: 2209128 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.7138. Min Act: -0.1700
Data Index: 5832131 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.6825. Min Act: -0.1700
Data Index: 231796 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.7138. Min Act: -0.1700
Data Index: 6636841 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.7138. Min Act: -0.1700
Data Index: 4623672 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.6825. Min Act: -0.1700
Data Index: 5571429 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.7138. Min Act: -0.1700
Data Index: 2868337 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.7138. Min Act: -0.1700
Data Index: 7554230 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.6513. Min Act: -0.1700
Data Index: 7966201 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.6825. Min Act: -0.1700
Data Index: 4472014 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.6825. Min Act: -0.1700
Data Index: 4431426 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.6513. Min Act: -0.1700
Data Index: 5736485 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8388. Min Range: -6.8388
Max Act: 6.6513. Min Act: -0.1700
Data Index: 3046387 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19