Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 866 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4297. Min Range: -8.4297
Max Act: 8.4297. Min Act: -0.1700
Data Index: 8784246 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4297. Min Range: -8.4297
Max Act: 8.3672. Min Act: -0.1700
Data Index: 1136406 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4297. Min Range: -8.4297
Max Act: 8.3047. Min Act: -0.1700
Data Index: 6915704 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4297. Min Range: -8.4297
Max Act: 8.3047. Min Act: -0.1700
Data Index: 6308636 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4297. Min Range: -8.4297
Max Act: 8.3047. Min Act: -0.1700
Data Index: 7388799 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4297. Min Range: -8.4297
Max Act: 8.2422. Min Act: -0.1700
Data Index: 3885969 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4297. Min Range: -8.4297
Max Act: 8.1797. Min Act: -0.1700
Data Index: 7755945 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4297. Min Range: -8.4297
Max Act: 8.1797. Min Act: -0.1700
Data Index: 7318615 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4297. Min Range: -8.4297
Max Act: 8.1797. Min Act: -0.1700
Data Index: 3245063 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4297. Min Range: -8.4297
Max Act: 8.0547. Min Act: -0.1700
Data Index: 1916327 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4297. Min Range: -8.4297
Max Act: 7.9922. Min Act: -0.1700
Data Index: 4605519 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4297. Min Range: -8.4297
Max Act: 7.9922. Min Act: -0.1700
Data Index: 6787283 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4297. Min Range: -8.4297
Max Act: 7.9922. Min Act: -0.1700
Data Index: 4419988 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4297. Min Range: -8.4297
Max Act: 7.9922. Min Act: -0.1700
Data Index: 6053054 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4297. Min Range: -8.4297
Max Act: 7.9922. Min Act: -0.1700
Data Index: 7222588 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4297. Min Range: -8.4297
Max Act: 7.9922. Min Act: -0.1700
Data Index: 2719823 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4297. Min Range: -8.4297
Max Act: 7.9922. Min Act: -0.1700
Data Index: 7090825 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4297. Min Range: -8.4297
Max Act: 7.9297. Min Act: -0.1700
Data Index: 5407187 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4297. Min Range: -8.4297
Max Act: 7.9922. Min Act: -0.1700
Data Index: 733418 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4297. Min Range: -8.4297
Max Act: 7.9297. Min Act: -0.1700
Data Index: 2529666 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19