Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 587 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.3346. Min Act: -0.1700
Data Index: 3422943 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.3033. Min Act: -0.1700
Data Index: 7679109 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.3033. Min Act: -0.1700
Data Index: 522139 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.3033. Min Act: -0.1700
Data Index: 943780 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.2408. Min Act: -0.1700
Data Index: 2641773 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.2408. Min Act: -0.1700
Data Index: 3013143 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.2721. Min Act: -0.1700
Data Index: 6249299 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.2096. Min Act: -0.1700
Data Index: 6120278 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.2096. Min Act: -0.1700
Data Index: 4622916 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.2096. Min Act: -0.1700
Data Index: 1709206 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.2408. Min Act: -0.1700
Data Index: 8789636 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.2096. Min Act: -0.1700
Data Index: 812732 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.2096. Min Act: -0.1700
Data Index: 8766445 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.1470. Min Act: -0.1700
Data Index: 6879383 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.1470. Min Act: -0.1700
Data Index: 7455069 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.1158. Min Act: -0.1700
Data Index: 6879370 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.1470. Min Act: -0.1700
Data Index: 5364742 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.1470. Min Act: -0.1700
Data Index: 1302149 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.1470. Min Act: -0.1700
Data Index: 2002898 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3346. Min Range: -4.3346
Max Act: 4.1158. Min Act: -0.1700
Data Index: 4160651 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19