Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.7538. Min Act: -0.1700
Data Index: 2566107 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4725. Min Act: -0.1700
Data Index: 7425243 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4100. Min Act: -0.1700
Data Index: 4517183 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.3163. Min Act: -0.1700
Data Index: 2258787 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.3163. Min Act: -0.1700
Data Index: 4190476 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.3163. Min Act: -0.1700
Data Index: 4463389 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.2850. Min Act: -0.1700
Data Index: 3848714 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.2850. Min Act: -0.1700
Data Index: 2002454 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.2850. Min Act: -0.1700
Data Index: 3002826 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.2850. Min Act: -0.1700
Data Index: 5407576 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.2538. Min Act: -0.1700
Data Index: 6448404 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.2538. Min Act: -0.1700
Data Index: 8030913 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.2538. Min Act: -0.1700
Data Index: 2045045 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.2850. Min Act: -0.1700
Data Index: 1537812 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.2538. Min Act: -0.1700
Data Index: 2999555 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1913. Min Act: -0.1700
Data Index: 6226029 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1913. Min Act: -0.1700
Data Index: 779253 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1913. Min Act: -0.1700
Data Index: 61331 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1288. Min Act: -0.1700
Data Index: 2605650 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1600. Min Act: -0.1700
Data Index: 2881863 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19