Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1028 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2662. Min Range: -5.2662
Max Act: 5.2662. Min Act: -0.1700
Data Index: 8377702 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2662. Min Range: -5.2662
Max Act: 5.1724. Min Act: -0.1700
Data Index: 3738332 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2662. Min Range: -5.2662
Max Act: 5.0474. Min Act: -0.1700
Data Index: 4881671 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2662. Min Range: -5.2662
Max Act: 5.0474. Min Act: -0.1700
Data Index: 704249 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2662. Min Range: -5.2662
Max Act: 5.0162. Min Act: -0.1700
Data Index: 787100 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.9849. Min Act: -0.1700
Data Index: 5059475 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.9537. Min Act: -0.1700
Data Index: 923093 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.9849. Min Act: -0.1700
Data Index: 38914 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.9537. Min Act: -0.1700
Data Index: 6683384 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.8912. Min Act: -0.1700
Data Index: 4463745 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.9537. Min Act: -0.1700
Data Index: 4753359 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.9224. Min Act: -0.1700
Data Index: 4753355 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.9224. Min Act: -0.1700
Data Index: 7412064 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.9224. Min Act: -0.1700
Data Index: 787097 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.9224. Min Act: -0.1700
Data Index: 363819 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.9224. Min Act: -0.1700
Data Index: 3165 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.8912. Min Act: -0.1700
Data Index: 1237138 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.8912. Min Act: -0.1700
Data Index: 4753357 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.8599. Min Act: -0.1700
Data Index: 749157 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2662. Min Range: -5.2662
Max Act: 4.8599. Min Act: -0.1700
Data Index: 4289326 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19