Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.3703. Min Act: -0.1700
Data Index: 5692609 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.3078. Min Act: -0.1700
Data Index: 5801317 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.3390. Min Act: -0.1700
Data Index: 384736 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.2453. Min Act: -0.1700
Data Index: 5949432 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.2765. Min Act: -0.1700
Data Index: 365342 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.2140. Min Act: -0.1700
Data Index: 607383 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.2140. Min Act: -0.1700
Data Index: 5735784 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.1515. Min Act: -0.1700
Data Index: 7741313 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.1828. Min Act: -0.1700
Data Index: 4408917 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.1828. Min Act: -0.1700
Data Index: 4614311 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.1203. Min Act: -0.1700
Data Index: 356257 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.1515. Min Act: -0.1699
Data Index: 4631390 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.1515. Min Act: -0.1700
Data Index: 8231131 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.1203. Min Act: -0.1700
Data Index: 8074471 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.0890. Min Act: -0.1700
Data Index: 1553607 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.1203. Min Act: -0.1700
Data Index: 1741517 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.0890. Min Act: -0.1700
Data Index: 4853219 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.0890. Min Act: -0.1700
Data Index: 7481622 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.0578. Min Act: -0.1700
Data Index: 3315243 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3703. Min Range: -4.3703
Max Act: 4.1203. Min Act: -0.1700
Data Index: 2060674 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19