Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2174 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.8865. Min Act: -0.1700
Data Index: 7538289 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.8865. Min Act: -0.1700
Data Index: 4300014 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.7615. Min Act: -0.1700
Data Index: 2583801 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.7615. Min Act: -0.1700
Data Index: 3971113 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.7615. Min Act: -0.1700
Data Index: 2483214 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.7615. Min Act: -0.1700
Data Index: 2870224 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6990. Min Act: -0.1700
Data Index: 838166 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6990. Min Act: -0.1698
Data Index: 4014960 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6990. Min Act: -0.1700
Data Index: 5356414 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6990. Min Act: -0.1698
Data Index: 8290730 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6365. Min Act: -0.1700
Data Index: 2349533 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6365. Min Act: -0.1698
Data Index: 7897352 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6052. Min Act: -0.1700
Data Index: 4667670 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6677. Min Act: -0.1696
Data Index: 1537097 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6052. Min Act: -0.1700
Data Index: 4605235 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6365. Min Act: -0.1700
Data Index: 7575957 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6052. Min Act: -0.1700
Data Index: 2375352 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6052. Min Act: -0.1700
Data Index: 7265586 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6365. Min Act: -0.1699
Data Index: 3055534 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8865. Min Range: -6.8865
Max Act: 6.6052. Min Act: -0.1700
Data Index: 7492938 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19