Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1665 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.9695. Min Act: -0.1700
Data Index: 4539983 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.9382. Min Act: -0.1700
Data Index: 5486089 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.8132. Min Act: -0.1700
Data Index: 5940564 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.6257. Min Act: -0.1700
Data Index: 4444656 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.7195. Min Act: -0.1700
Data Index: 4594266 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.6257. Min Act: -0.1700
Data Index: 983090 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.6882. Min Act: -0.1700
Data Index: 2665763 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.6570. Min Act: -0.1700
Data Index: 8132018 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.6882. Min Act: -0.1700
Data Index: 267086 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.6257. Min Act: -0.1700
Data Index: 156533 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.6257. Min Act: -0.1700
Data Index: 976675 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.6257. Min Act: -0.1700
Data Index: 1372034 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.6257. Min Act: -0.1700
Data Index: 269281 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.5632. Min Act: -0.1700
Data Index: 2018117 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.5632. Min Act: -0.1700
Data Index: 3756430 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.5632. Min Act: -0.1700
Data Index: 6753569 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.5320. Min Act: -0.1700
Data Index: 997810 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.5945. Min Act: -0.1700
Data Index: 21505 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.5632. Min Act: -0.1700
Data Index: 2097692 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9695. Min Range: -5.9695
Max Act: 5.5320. Min Act: -0.1700
Data Index: 968072 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19