Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.7162. Min Act: -0.1700
Data Index: 3981673 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.5600. Min Act: -0.1700
Data Index: 4619315 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4975. Min Act: -0.1700
Data Index: 4470784 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.3412. Min Act: -0.1700
Data Index: 6471637 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.3100. Min Act: -0.1700
Data Index: 6549201 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.2787. Min Act: -0.1700
Data Index: 3945810 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.3100. Min Act: -0.1700
Data Index: 2706219 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.1850. Min Act: -0.1700
Data Index: 7290173 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.2787. Min Act: -0.1700
Data Index: 1417072 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.2475. Min Act: -0.1700
Data Index: 4984097 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.2162. Min Act: -0.1700
Data Index: 5244912 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.2162. Min Act: -0.1700
Data Index: 7437101 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.2475. Min Act: -0.1700
Data Index: 4125938 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.1850. Min Act: -0.1700
Data Index: 3682680 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.1850. Min Act: -0.1700
Data Index: 5956692 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.2162. Min Act: -0.1700
Data Index: 2645431 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.1537. Min Act: -0.1700
Data Index: 292503 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.2162. Min Act: -0.1700
Data Index: 3092347 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.2162. Min Act: -0.1700
Data Index: 3477230 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.1537. Min Act: -0.1700
Data Index: 4518392 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19