Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1778 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.1085. Min Act: -0.1700
Data Index: 1909351 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.1397. Min Act: -0.1700
Data Index: 1608386 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.1085. Min Act: -0.1700
Data Index: 5010809 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0772. Min Act: -0.1700
Data Index: 2580149 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.1085. Min Act: -0.1700
Data Index: 5402329 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0460. Min Act: -0.1700
Data Index: 317142 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0147. Min Act: -0.1700
Data Index: 4286139 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0460. Min Act: -0.1700
Data Index: 5559191 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0772. Min Act: -0.1700
Data Index: 4150072 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0460. Min Act: -0.1700
Data Index: 135391 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0147. Min Act: -0.1700
Data Index: 5223687 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0460. Min Act: -0.1700
Data Index: 7791677 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1397. Min Range: -5.1397
Max Act: 4.9835. Min Act: -0.1700
Data Index: 3713112 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0147. Min Act: -0.1700
Data Index: 3693406 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0147. Min Act: -0.1700
Data Index: 5748025 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0147. Min Act: -0.1700
Data Index: 1045522 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0147. Min Act: -0.1700
Data Index: 3303874 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0147. Min Act: -0.1700
Data Index: 731943 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0147. Min Act: -0.1700
Data Index: 1895343 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1397. Min Range: -5.1397
Max Act: 5.0147. Min Act: -0.1700
Data Index: 4369665 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19