Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 816 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1108. Min Range: -3.1108
Max Act: 3.1108. Min Act: -0.1700
Data Index: 2638981 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1108. Min Range: -3.1108
Max Act: 3.0793. Min Act: -0.1700
Data Index: 6163044 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1108. Min Range: -3.1108
Max Act: 3.0635. Min Act: -0.1700
Data Index: 51162 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1108. Min Range: -3.1108
Max Act: 3.0162. Min Act: -0.1700
Data Index: 6045467 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.9687. Min Act: -0.1700
Data Index: 6095592 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.9846. Min Act: -0.1700
Data Index: 1992253 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.9687. Min Act: -0.1700
Data Index: 3242259 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.9529. Min Act: -0.1700
Data Index: 5335930 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.9212. Min Act: -0.1700
Data Index: 5618606 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.9371. Min Act: -0.1700
Data Index: 2837322 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.9054. Min Act: -0.1700
Data Index: 8572987 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.8737. Min Act: -0.1700
Data Index: 3269570 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.9054. Min Act: -0.1700
Data Index: 5956816 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.8895. Min Act: -0.1700
Data Index: 8815916 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.8895. Min Act: -0.1700
Data Index: 3817944 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.8895. Min Act: -0.1700
Data Index: 414190 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.8737. Min Act: -0.1700
Data Index: 745265 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.9212. Min Act: -0.1700
Data Index: 3491818 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.8578. Min Act: -0.1700
Data Index: 8227512 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1108. Min Range: -3.1108
Max Act: 2.8578. Min Act: -0.1700
Data Index: 5179960 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19