Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6155. Min Range: -6.6155
Max Act: 6.6155. Min Act: -0.1700
Data Index: 8476079 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6155. Min Range: -6.6155
Max Act: 6.3342. Min Act: -0.1700
Data Index: 6407551 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6155. Min Range: -6.6155
Max Act: 6.2717. Min Act: -0.1700
Data Index: 654417 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6155. Min Range: -6.6155
Max Act: 6.2092. Min Act: -0.1700
Data Index: 4701325 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6155. Min Range: -6.6155
Max Act: 6.1155. Min Act: -0.1700
Data Index: 4602789 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6155. Min Range: -6.6155
Max Act: 6.0842. Min Act: -0.1700
Data Index: 4672021 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6155. Min Range: -6.6155
Max Act: 6.1155. Min Act: -0.1700
Data Index: 1268247 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.9905. Min Act: -0.1700
Data Index: 6787846 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6155. Min Range: -6.6155
Max Act: 6.0530. Min Act: -0.1700
Data Index: 3861676 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.9592. Min Act: -0.1700
Data Index: 7407015 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.9280. Min Act: -0.1700
Data Index: 8428101 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.8967. Min Act: -0.1700
Data Index: 8158663 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.9280. Min Act: -0.1700
Data Index: 7970699 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.8967. Min Act: -0.1700
Data Index: 3911295 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.8967. Min Act: -0.1700
Data Index: 7077352 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.8655. Min Act: -0.1700
Data Index: 1439443 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.8655. Min Act: -0.1700
Data Index: 4172877 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.8342. Min Act: -0.1700
Data Index: 3857414 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.8342. Min Act: -0.1700
Data Index: 1390631 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6155. Min Range: -6.6155
Max Act: 5.8342. Min Act: -0.1700
Data Index: 852104 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19