Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1578 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9850. Min Act: -0.1700
Data Index: 5436657 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9850. Min Act: -0.1700
Data Index: 354040 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9850. Min Act: -0.1700
Data Index: 6961478 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9850. Min Act: -0.1700
Data Index: 7910027 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9538. Min Act: -0.1700
Data Index: 4960460 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9538. Min Act: -0.1700
Data Index: 8382669 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9538. Min Act: -0.1700
Data Index: 3400161 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.8913. Min Act: -0.1700
Data Index: 8785870 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9538. Min Act: -0.1700
Data Index: 6585053 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9225. Min Act: -0.1700
Data Index: 1113329 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9225. Min Act: -0.1700
Data Index: 3482145 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9538. Min Act: -0.1700
Data Index: 4351010 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9225. Min Act: -0.1700
Data Index: 6323438 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9225. Min Act: -0.1700
Data Index: 4028670 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.8913. Min Act: -0.1700
Data Index: 3897299 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.8913. Min Act: -0.1700
Data Index: 8293278 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9225. Min Act: -0.1700
Data Index: 7968894 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9225. Min Act: -0.1700
Data Index: 7545451 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.8913. Min Act: -0.1700
Data Index: 2228000 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9225. Min Act: -0.1700
Data Index: 6727691 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19