Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 354 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1394. Min Range: -5.1394
Max Act: 5.1394. Min Act: -0.1700
Data Index: 5345783 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1394. Min Range: -5.1394
Max Act: 5.0144. Min Act: -0.1700
Data Index: 7809858 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.9832. Min Act: -0.1700
Data Index: 3349676 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.9832. Min Act: -0.1700
Data Index: 2635183 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.9832. Min Act: -0.1700
Data Index: 1480794 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.9207. Min Act: -0.1700
Data Index: 146060 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.9519. Min Act: -0.1700
Data Index: 8683966 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.9207. Min Act: -0.1700
Data Index: 7298912 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.8894. Min Act: -0.1700
Data Index: 4838605 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.8582. Min Act: -0.1700
Data Index: 1067018 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.8582. Min Act: -0.1700
Data Index: 6847928 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.8894. Min Act: -0.1700
Data Index: 7961300 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.8582. Min Act: -0.1700
Data Index: 6819521 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.8582. Min Act: -0.1700
Data Index: 6268915 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.8582. Min Act: -0.1700
Data Index: 2004485 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.8582. Min Act: -0.1700
Data Index: 7764939 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.8582. Min Act: -0.1700
Data Index: 7598997 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.8894. Min Act: -0.1700
Data Index: 3727040 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.7957. Min Act: -0.1700
Data Index: 1556643 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1394. Min Range: -5.1394
Max Act: 4.7957. Min Act: -0.1700
Data Index: 5838932 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19