Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.5706. Min Act: -0.1699
Data Index: 8761724 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.5394. Min Act: -0.1700
Data Index: 3258262 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.4769. Min Act: -0.1700
Data Index: 3262433 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.3831. Min Act: -0.1700
Data Index: 8278712 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.2581. Min Act: -0.1700
Data Index: 1398053 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.1956. Min Act: -0.1700
Data Index: 5095000 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.1956. Min Act: -0.1700
Data Index: 4960953 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.1956. Min Act: -0.1700
Data Index: 7057521 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.1644. Min Act: -0.1700
Data Index: 908694 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.1644. Min Act: -0.1700
Data Index: 2737540 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.1644. Min Act: -0.1700
Data Index: 3078591 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.1644. Min Act: -0.1700
Data Index: 2429969 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.1644. Min Act: -0.1700
Data Index: 6929816 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.1019. Min Act: -0.1700
Data Index: 5313420 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.0706. Min Act: -0.1700
Data Index: 3750327 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.1019. Min Act: -0.1700
Data Index: 5257126 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.0706. Min Act: -0.1700
Data Index: 7201759 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.0706. Min Act: -0.1700
Data Index: 6545310 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.0394. Min Act: -0.1700
Data Index: 2925819 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5706. Min Range: -5.5706
Max Act: 5.0394. Min Act: -0.1700
Data Index: 7626697 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19