Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3345 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.9249. Min Act: -0.1700
Data Index: 6923948 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.8624. Min Act: -0.1700
Data Index: 4433553 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.7686. Min Act: -0.1700
Data Index: 7980193 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.7374. Min Act: -0.1700
Data Index: 2255658 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.7374. Min Act: -0.1700
Data Index: 6295639 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.7374. Min Act: -0.1700
Data Index: 213315 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.7061. Min Act: -0.1700
Data Index: 962093 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.7061. Min Act: -0.1700
Data Index: 8409105 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.6749. Min Act: -0.1700
Data Index: 4359474 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.7061. Min Act: -0.1700
Data Index: 5042915 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.6436. Min Act: -0.1700
Data Index: 4103415 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.6436. Min Act: -0.1700
Data Index: 3176846 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.6436. Min Act: -0.1700
Data Index: 4818582 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.6124. Min Act: -0.1700
Data Index: 1884349 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.6124. Min Act: -0.1700
Data Index: 2170774 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.6124. Min Act: -0.1700
Data Index: 6128771 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.6124. Min Act: -0.1700
Data Index: 8771376 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.6124. Min Act: -0.1700
Data Index: 5383119 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.5499. Min Act: -0.1700
Data Index: 2834249 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9249. Min Range: -4.9249
Max Act: 4.5811. Min Act: -0.1700
Data Index: 8281368 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19