Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2116 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.9525. Min Act: -0.1700
Data Index: 3557243 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.7963. Min Act: -0.1700
Data Index: 3776600 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.6400. Min Act: -0.1700
Data Index: 771834 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.6400. Min Act: -0.1700
Data Index: 8314914 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.6088. Min Act: -0.1700
Data Index: 1468265 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.5463. Min Act: -0.1700
Data Index: 560633 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.5775. Min Act: -0.1700
Data Index: 4207707 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.5775. Min Act: -0.1700
Data Index: 6267200 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.5150. Min Act: -0.1700
Data Index: 64632 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.5463. Min Act: -0.1700
Data Index: 2251609 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.5463. Min Act: -0.1700
Data Index: 4661549 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.5150. Min Act: -0.1700
Data Index: 775621 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.5150. Min Act: -0.1700
Data Index: 8772868 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.4838. Min Act: -0.1700
Data Index: 4876828 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.4525. Min Act: -0.1700
Data Index: 3705892 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.4525. Min Act: -0.1700
Data Index: 3848243 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.4525. Min Act: -0.1700
Data Index: 5960513 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.4213. Min Act: -0.1700
Data Index: 4058294 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.4213. Min Act: -0.1700
Data Index: 205841 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9525. Min Range: -5.9525
Max Act: 5.3900. Min Act: -0.1700
Data Index: 268509 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19