Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2176 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4444. Min Range: -8.4444
Max Act: 8.4444. Min Act: -0.1700
Data Index: 784508 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4444. Min Range: -8.4444
Max Act: 8.3194. Min Act: -0.1700
Data Index: 3569 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4444. Min Range: -8.4444
Max Act: 8.3194. Min Act: -0.1700
Data Index: 1955479 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4444. Min Range: -8.4444
Max Act: 8.1944. Min Act: -0.1700
Data Index: 4409772 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4444. Min Range: -8.4444
Max Act: 8.1319. Min Act: -0.1700
Data Index: 5854506 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4444. Min Range: -8.4444
Max Act: 8.1006. Min Act: -0.1700
Data Index: 3386050 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4444. Min Range: -8.4444
Max Act: 8.0381. Min Act: -0.1700
Data Index: 7801389 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4444. Min Range: -8.4444
Max Act: 8.1319. Min Act: -0.1700
Data Index: 5052610 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4444. Min Range: -8.4444
Max Act: 8.0694. Min Act: -0.1700
Data Index: 2111420 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4444. Min Range: -8.4444
Max Act: 7.9131. Min Act: -0.1700
Data Index: 1690804 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4444. Min Range: -8.4444
Max Act: 7.9444. Min Act: -0.1700
Data Index: 5228029 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4444. Min Range: -8.4444
Max Act: 7.8819. Min Act: -0.1700
Data Index: 5505624 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4444. Min Range: -8.4444
Max Act: 7.8506. Min Act: -0.1700
Data Index: 7466327 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4444. Min Range: -8.4444
Max Act: 7.8506. Min Act: -0.1700
Data Index: 6509092 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4444. Min Range: -8.4444
Max Act: 7.8194. Min Act: -0.1700
Data Index: 4702811 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4444. Min Range: -8.4444
Max Act: 7.7256. Min Act: -0.1700
Data Index: 6985252 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4444. Min Range: -8.4444
Max Act: 7.6631. Min Act: -0.1700
Data Index: 1515113 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4444. Min Range: -8.4444
Max Act: 7.6944. Min Act: -0.1700
Data Index: 2462200 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4444. Min Range: -8.4444
Max Act: 7.6944. Min Act: -0.1700
Data Index: 3900246 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4444. Min Range: -8.4444
Max Act: 7.6944. Min Act: -0.1700
Data Index: 1001811 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19