Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1467 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.5451. Min Act: -0.1700
Data Index: 682294 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.5139. Min Act: -0.1700
Data Index: 1692730 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.4514. Min Act: -0.1700
Data Index: 4211831 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.4201. Min Act: -0.1700
Data Index: 6959200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.4201. Min Act: -0.1700
Data Index: 6040123 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.3889. Min Act: -0.1700
Data Index: 6278004 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.3576. Min Act: -0.1700
Data Index: 4170406 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.3264. Min Act: -0.1700
Data Index: 1397171 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.2639. Min Act: -0.1700
Data Index: 8197174 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.2326. Min Act: -0.1700
Data Index: 2889139 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.2326. Min Act: -0.1700
Data Index: 621619 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.2014. Min Act: -0.1700
Data Index: 7205552 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.2014. Min Act: -0.1700
Data Index: 8123710 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.2014. Min Act: -0.1700
Data Index: 2072899 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.1701. Min Act: -0.1700
Data Index: 2209639 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.1701. Min Act: -0.1700
Data Index: 571322 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.1701. Min Act: -0.1700
Data Index: 7970520 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.1701. Min Act: -0.1700
Data Index: 5122352 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.1389. Min Act: -0.1700
Data Index: 3104720 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5451. Min Range: -4.5451
Max Act: 4.2014. Min Act: -0.1700
Data Index: 7690030 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19