Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 288 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.4487. Min Act: -0.1700
Data Index: 655015 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.4017. Min Act: -0.1700
Data Index: 5733864 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.3860. Min Act: -0.1700
Data Index: 1593706 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.3860. Min Act: -0.1700
Data Index: 1122216 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.3703. Min Act: -0.1700
Data Index: 7177487 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.3860. Min Act: -0.1700
Data Index: 3584970 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.3860. Min Act: -0.1700
Data Index: 1269841 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.3389. Min Act: -0.1700
Data Index: 6939551 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.3389. Min Act: -0.1700
Data Index: 8456330 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.3075. Min Act: -0.1700
Data Index: 8048922 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.3075. Min Act: -0.1700
Data Index: 2187533 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.3389. Min Act: -0.1700
Data Index: 1191447 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.2918. Min Act: -0.1700
Data Index: 6939552 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.2918. Min Act: -0.1700
Data Index: 4896773 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.2604. Min Act: -0.1700
Data Index: 1558683 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.2604. Min Act: -0.1700
Data Index: 5297919 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.2761. Min Act: -0.1700
Data Index: 4178735 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.2761. Min Act: -0.1700
Data Index: 5113627 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.2447. Min Act: -0.1700
Data Index: 4161396 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4487. Min Range: -3.4487
Max Act: 3.2761. Min Act: -0.1700
Data Index: 2365508 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19