Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2181 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.4474. Min Act: -0.1700
Data Index: 3366529 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.3849. Min Act: -0.1700
Data Index: 3478451 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.4162. Min Act: -0.1700
Data Index: 8163839 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.2912. Min Act: -0.1700
Data Index: 6285014 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.2912. Min Act: -0.1700
Data Index: 2202830 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.2287. Min Act: -0.1700
Data Index: 7534354 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.2599. Min Act: -0.1700
Data Index: 2994750 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.2287. Min Act: -0.1700
Data Index: 4522546 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.1974. Min Act: -0.1700
Data Index: 3112622 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.2287. Min Act: -0.1700
Data Index: 6920395 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.2287. Min Act: -0.1700
Data Index: 3957579 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.1349. Min Act: -0.1700
Data Index: 8671292 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.1662. Min Act: -0.1700
Data Index: 6816637 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.1662. Min Act: -0.1700
Data Index: 572262 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.1662. Min Act: -0.1700
Data Index: 6490401 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.1662. Min Act: -0.1700
Data Index: 524070 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.1662. Min Act: -0.1700
Data Index: 8793541 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.1349. Min Act: -0.1700
Data Index: 1821538 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.1037. Min Act: -0.1700
Data Index: 8151720 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4474. Min Range: -5.4474
Max Act: 5.1037. Min Act: -0.1700
Data Index: 6076135 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19