Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4081 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0877. Min Range: -8.0877
Max Act: 8.0877. Min Act: -0.1700
Data Index: 6281553 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0877. Min Range: -8.0877
Max Act: 8.0565. Min Act: -0.1700
Data Index: 3818033 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.9002. Min Act: -0.1700
Data Index: 3724758 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.8377. Min Act: -0.1700
Data Index: 7658404 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.8377. Min Act: -0.1700
Data Index: 6281552 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.7440. Min Act: -0.1700
Data Index: 6845360 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.8377. Min Act: -0.1700
Data Index: 7658405 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.7440. Min Act: -0.1700
Data Index: 8506108 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.7127. Min Act: -0.1700
Data Index: 2109380 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0877. Min Range: -8.0877
Max Act: 6.5565. Min Act: -0.1700
Data Index: 513950 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.7127. Min Act: -0.1700
Data Index: 185175 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.6190. Min Act: -0.1700
Data Index: 5136880 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.6502. Min Act: -0.1700
Data Index: 1291276 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.6815. Min Act: -0.1700
Data Index: 2109377 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.5252. Min Act: -0.1700
Data Index: 8449406 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.4940. Min Act: -0.1700
Data Index: 2970616 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.4002. Min Act: -0.1700
Data Index: 8510691 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.4315. Min Act: -0.1700
Data Index: 1048452 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.4627. Min Act: -0.1700
Data Index: 6154701 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0877. Min Range: -8.0877
Max Act: 7.4940. Min Act: -0.1700
Data Index: 495354 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19