Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5065 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.6521. Min Act: -0.1700
Data Index: 8060593 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.5896. Min Act: -0.1700
Data Index: 6618803 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.5896. Min Act: -0.1700
Data Index: 6592263 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.5271. Min Act: -0.1700
Data Index: 1067860 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.4646. Min Act: -0.1700
Data Index: 3423521 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.4021. Min Act: -0.1700
Data Index: 2499353 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.4646. Min Act: -0.1700
Data Index: 763481 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.3396. Min Act: -0.1700
Data Index: 5750427 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.4021. Min Act: -0.1700
Data Index: 4661913 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.2771. Min Act: -0.1700
Data Index: 4461721 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.2771. Min Act: -0.1700
Data Index: 8066513 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.1521. Min Act: -0.1700
Data Index: 5611156 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.2146. Min Act: -0.1700
Data Index: 5063474 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.2146. Min Act: -0.1700
Data Index: 6589237 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.1521. Min Act: -0.1700
Data Index: 3904171 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.1521. Min Act: -0.1700
Data Index: 524991 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.2146. Min Act: -0.1700
Data Index: 2609647 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.1521. Min Act: -0.1700
Data Index: 389103 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.1521. Min Act: -0.1700
Data Index: 8059645 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6521. Min Range: -8.6521
Max Act: 8.1521. Min Act: -0.1700
Data Index: 2402560 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19