Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4084 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.1706. Min Act: -0.1700
Data Index: 5157717 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.1081. Min Act: -0.1700
Data Index: 2294324 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.1394. Min Act: -0.1700
Data Index: 4674332 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.1081. Min Act: -0.1700
Data Index: 5493600 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0456. Min Act: -0.1700
Data Index: 3780709 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0768. Min Act: -0.1700
Data Index: 2199031 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0456. Min Act: -0.1700
Data Index: 7603360 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0456. Min Act: -0.1700
Data Index: 239877 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0456. Min Act: -0.1700
Data Index: 1491970 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0143. Min Act: -0.1700
Data Index: 5857189 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0456. Min Act: -0.1700
Data Index: 4622959 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0143. Min Act: -0.1700
Data Index: 6301568 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0143. Min Act: -0.1700
Data Index: 4895647 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0456. Min Act: -0.1700
Data Index: 3122548 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0143. Min Act: -0.1700
Data Index: 2017866 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0143. Min Act: -0.1700
Data Index: 3906089 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1706. Min Range: -4.1706
Max Act: 4.0143. Min Act: -0.1700
Data Index: 2667666 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1706. Min Range: -4.1706
Max Act: 3.9831. Min Act: -0.1700
Data Index: 2850656 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1706. Min Range: -4.1706
Max Act: 3.9518. Min Act: -0.1700
Data Index: 5753869 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1706. Min Range: -4.1706
Max Act: 3.9518. Min Act: -0.1700
Data Index: 2731268 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19