Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1997 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3636. Min Range: -9.3636
Max Act: 9.3636. Min Act: -0.1700
Data Index: 3997756 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.9886. Min Act: -0.1700
Data Index: 1120283 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.9261. Min Act: -0.1700
Data Index: 2036724 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.9261. Min Act: -0.1700
Data Index: 5342396 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.8636. Min Act: -0.1700
Data Index: 6641983 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.8636. Min Act: -0.1700
Data Index: 4736465 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.7386. Min Act: -0.1700
Data Index: 3391828 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.7386. Min Act: -0.1700
Data Index: 6791858 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.6136. Min Act: -0.1700
Data Index: 8086964 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.6136. Min Act: -0.1700
Data Index: 7517409 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.6136. Min Act: -0.1700
Data Index: 6453449 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.5511. Min Act: -0.1700
Data Index: 5942795 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.6136. Min Act: -0.1700
Data Index: 5141280 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.5511. Min Act: -0.1700
Data Index: 772239 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.6136. Min Act: -0.1700
Data Index: 4098563 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.6136. Min Act: -0.1700
Data Index: 8418647 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.5511. Min Act: -0.1700
Data Index: 3460297 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.5511. Min Act: -0.1700
Data Index: 6829563 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.5511. Min Act: -0.1700
Data Index: 7935134 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3636. Min Range: -9.3636
Max Act: 8.4886. Min Act: -0.1700
Data Index: 4517970 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19