Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 757 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.7271. Min Range: -10.7271
Max Act: 10.7271. Min Act: -0.1700
Data Index: 7332229 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.9771. Min Act: -0.1700
Data Index: 1545161 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.9771. Min Act: -0.1700
Data Index: 5313250 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.9146. Min Act: -0.1700
Data Index: 1580197 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.8521. Min Act: -0.1700
Data Index: 7332224 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.7896. Min Act: -0.1700
Data Index: 5143141 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.7271. Min Act: -0.1700
Data Index: 4477739 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.7271. Min Act: -0.1700
Data Index: 2368635 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.5396. Min Act: -0.1700
Data Index: 1403848 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.5396. Min Act: -0.1700
Data Index: 1587786 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.6021. Min Act: -0.1700
Data Index: 3330907 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.5396. Min Act: -0.1700
Data Index: 1403851 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.5396. Min Act: -0.1700
Data Index: 5445814 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.4771. Min Act: -0.1700
Data Index: 4292348 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.4771. Min Act: -0.1700
Data Index: 4014254 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.4146. Min Act: -0.1700
Data Index: 2882048 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.4146. Min Act: -0.1700
Data Index: 3361199 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.3521. Min Act: -0.1700
Data Index: 6077429 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.3521. Min Act: -0.1700
Data Index: 897607 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7271. Min Range: -10.7271
Max Act: 9.2896. Min Act: -0.1700
Data Index: 2304621 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19