Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1915. Min Range: -6.1915
Max Act: 6.1915. Min Act: -0.1700
Data Index: 4962283 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1915. Min Range: -6.1915
Max Act: 6.1290. Min Act: -0.1700
Data Index: 8679442 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1915. Min Range: -6.1915
Max Act: 6.0665. Min Act: -0.1700
Data Index: 688121 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1915. Min Range: -6.1915
Max Act: 6.0665. Min Act: -0.1700
Data Index: 7110000 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.9727. Min Act: -0.1700
Data Index: 6040482 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.9415. Min Act: -0.1700
Data Index: 1534870 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.8790. Min Act: -0.1700
Data Index: 7893210 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.9415. Min Act: -0.1700
Data Index: 4924402 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.9102. Min Act: -0.1700
Data Index: 291867 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.8477. Min Act: -0.1700
Data Index: 415185 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.8477. Min Act: -0.1700
Data Index: 8247211 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.8477. Min Act: -0.1700
Data Index: 1526637 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.8165. Min Act: -0.1700
Data Index: 1067316 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.7852. Min Act: -0.1700
Data Index: 1203703 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.7852. Min Act: -0.1700
Data Index: 8394917 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.7227. Min Act: -0.1700
Data Index: 8275591 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.7852. Min Act: -0.1700
Data Index: 5876387 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.6602. Min Act: -0.1700
Data Index: 2251977 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.6915. Min Act: -0.1700
Data Index: 8225028 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1915. Min Range: -6.1915
Max Act: 5.7227. Min Act: -0.1700
Data Index: 1981852 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19