Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3610 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3023. Min Range: -6.3023
Max Act: 6.3023. Min Act: -0.1700
Data Index: 7456017 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3023. Min Range: -6.3023
Max Act: 6.0836. Min Act: -0.1700
Data Index: 3972754 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3023. Min Range: -6.3023
Max Act: 6.0836. Min Act: -0.1700
Data Index: 1945319 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.9898. Min Act: -0.1700
Data Index: 1609032 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.9898. Min Act: -0.1700
Data Index: 823650 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.9586. Min Act: -0.1700
Data Index: 4592128 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.9586. Min Act: -0.1700
Data Index: 5957115 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.9586. Min Act: -0.1700
Data Index: 2594359 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.8961. Min Act: -0.1700
Data Index: 6315020 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.9273. Min Act: -0.1700
Data Index: 6441332 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.9273. Min Act: -0.1700
Data Index: 8233555 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.8648. Min Act: -0.1700
Data Index: 368272 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.8961. Min Act: -0.1700
Data Index: 3815972 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.8023. Min Act: -0.1700
Data Index: 8605934 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.8336. Min Act: -0.1700
Data Index: 5872330 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.8023. Min Act: -0.1700
Data Index: 1536950 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.8336. Min Act: -0.1700
Data Index: 4753738 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.8023. Min Act: -0.1700
Data Index: 1918167 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.8648. Min Act: -0.1700
Data Index: 3410471 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3023. Min Range: -6.3023
Max Act: 5.8336. Min Act: -0.1700
Data Index: 3573069 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19