Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 894 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2441. Min Range: -5.2441
Max Act: 5.2441. Min Act: -0.1700
Data Index: 3507530 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2441. Min Range: -5.2441
Max Act: 5.2129. Min Act: -0.1700
Data Index: 8088812 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2441. Min Range: -5.2441
Max Act: 5.2129. Min Act: -0.1700
Data Index: 3278041 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2441. Min Range: -5.2441
Max Act: 5.1816. Min Act: -0.1700
Data Index: 597843 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2441. Min Range: -5.2441
Max Act: 5.1191. Min Act: -0.1700
Data Index: 7658166 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2441. Min Range: -5.2441
Max Act: 5.1191. Min Act: -0.1700
Data Index: 5650968 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2441. Min Range: -5.2441
Max Act: 5.0879. Min Act: -0.1700
Data Index: 3585916 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2441. Min Range: -5.2441
Max Act: 5.0566. Min Act: -0.1700
Data Index: 3597703 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2441. Min Range: -5.2441
Max Act: 5.0566. Min Act: -0.1700
Data Index: 7738387 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2441. Min Range: -5.2441
Max Act: 5.0254. Min Act: -0.1700
Data Index: 7227779 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2441. Min Range: -5.2441
Max Act: 4.9941. Min Act: -0.1700
Data Index: 1263071 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2441. Min Range: -5.2441
Max Act: 5.0254. Min Act: -0.1700
Data Index: 8046296 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2441. Min Range: -5.2441
Max Act: 4.9629. Min Act: -0.1700
Data Index: 347458 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2441. Min Range: -5.2441
Max Act: 4.9629. Min Act: -0.1700
Data Index: 815127 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2441. Min Range: -5.2441
Max Act: 4.9941. Min Act: -0.1700
Data Index: 913434 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2441. Min Range: -5.2441
Max Act: 4.9316. Min Act: -0.1700
Data Index: 6712901 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2441. Min Range: -5.2441
Max Act: 4.9316. Min Act: -0.1700
Data Index: 4537715 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2441. Min Range: -5.2441
Max Act: 4.9004. Min Act: -0.1700
Data Index: 1716128 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2441. Min Range: -5.2441
Max Act: 4.9316. Min Act: -0.1700
Data Index: 2541832 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2441. Min Range: -5.2441
Max Act: 4.9629. Min Act: -0.1700
Data Index: 7885291 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19