Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3439 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.7247. Min Act: -0.1700
Data Index: 1181464 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.7247. Min Act: -0.1700
Data Index: 1013631 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.6152. Min Act: -0.1700
Data Index: 6044685 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.5995. Min Act: -0.1700
Data Index: 2499005 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.5682. Min Act: -0.1700
Data Index: 2276477 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.5526. Min Act: -0.1700
Data Index: 2168171 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.5213. Min Act: -0.1700
Data Index: 4605311 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.5213. Min Act: -0.1700
Data Index: 3266291 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.5056. Min Act: -0.1700
Data Index: 1036940 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.5056. Min Act: -0.1700
Data Index: 4787552 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.4899. Min Act: -0.1700
Data Index: 4112271 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.5056. Min Act: -0.1700
Data Index: 5062573 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.4743. Min Act: -0.1700
Data Index: 5076066 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.4586. Min Act: -0.1700
Data Index: 4657779 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.4899. Min Act: -0.1700
Data Index: 1948110 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.4899. Min Act: -0.1700
Data Index: 5027776 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.4586. Min Act: -0.1700
Data Index: 1575165 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.4743. Min Act: -0.1700
Data Index: 5188006 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.4429. Min Act: -0.1700
Data Index: 5538140 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7247. Min Range: -3.7247
Max Act: 3.4116. Min Act: -0.1700
Data Index: 4947200 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19