Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2483. Min Range: -3.2483
Max Act: 3.2483. Min Act: -0.1700
Data Index: 2271270 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2483. Min Range: -3.2483
Max Act: 3.1697. Min Act: -0.1700
Data Index: 4431219 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.9963. Min Act: -0.1700
Data Index: 3362198 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.9646. Min Act: -0.1700
Data Index: 1673454 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.9330. Min Act: -0.1700
Data Index: 3562725 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.9330. Min Act: -0.1700
Data Index: 8017503 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.9013. Min Act: -0.1700
Data Index: 3683437 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.9171. Min Act: -0.1700
Data Index: 6655384 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.8695. Min Act: -0.1700
Data Index: 5251664 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.9013. Min Act: -0.1700
Data Index: 4393381 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.8854. Min Act: -0.1700
Data Index: 828581 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.8695. Min Act: -0.1700
Data Index: 3448623 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.8536. Min Act: -0.1700
Data Index: 7847330 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.8378. Min Act: -0.1700
Data Index: 8016776 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.8854. Min Act: -0.1700
Data Index: 7905316 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.8378. Min Act: -0.1700
Data Index: 1889255 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.8059. Min Act: -0.1700
Data Index: 7484308 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.8378. Min Act: -0.1700
Data Index: 363295 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.8219. Min Act: -0.1700
Data Index: 909044 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2483. Min Range: -3.2483
Max Act: 2.7900. Min Act: -0.1700
Data Index: 2984470 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19