Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2321 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8703. Min Act: -0.1700
Data Index: 543647 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8703. Min Act: -0.1700
Data Index: 2455792 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8226. Min Act: -0.1700
Data Index: 860333 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8544. Min Act: -0.1700
Data Index: 3904505 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8544. Min Act: -0.1700
Data Index: 292656 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8226. Min Act: -0.1700
Data Index: 4128648 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8385. Min Act: -0.1700
Data Index: 7988135 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8067. Min Act: -0.1700
Data Index: 2739366 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8226. Min Act: -0.1700
Data Index: 1986871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8067. Min Act: -0.1700
Data Index: 3950118 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8226. Min Act: -0.1700
Data Index: 7654243 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8067. Min Act: -0.1700
Data Index: 2050717 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7907. Min Act: -0.1700
Data Index: 4556336 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8226. Min Act: -0.1700
Data Index: 2149247 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8067. Min Act: -0.1700
Data Index: 5615974 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7907. Min Act: -0.1700
Data Index: 1617302 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7907. Min Act: -0.1700
Data Index: 1431476 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7907. Min Act: -0.1700
Data Index: 2073801 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7907. Min Act: -0.1700
Data Index: 4355136 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7907. Min Act: -0.1700
Data Index: 5421676 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19