Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 885 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.9148. Min Act: -0.1700
Data Index: 7557497 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.7898. Min Act: -0.1700
Data Index: 957463 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.7898. Min Act: -0.1700
Data Index: 6849702 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.7586. Min Act: -0.1700
Data Index: 1254936 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6961. Min Act: -0.1700
Data Index: 7450850 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6961. Min Act: -0.1700
Data Index: 5464973 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6961. Min Act: -0.1700
Data Index: 4716395 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6961. Min Act: -0.1700
Data Index: 1572976 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6648. Min Act: -0.1700
Data Index: 3464087 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6336. Min Act: -0.1700
Data Index: 6596094 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6336. Min Act: -0.1700
Data Index: 1497316 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6648. Min Act: -0.1700
Data Index: 1180272 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6336. Min Act: -0.1700
Data Index: 833623 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6023. Min Act: -0.1700
Data Index: 7518681 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6336. Min Act: -0.1700
Data Index: 1985680 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6023. Min Act: -0.1700
Data Index: 2786083 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.6023. Min Act: -0.1700
Data Index: 7490739 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.5711. Min Act: -0.1700
Data Index: 7854568 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.5711. Min Act: -0.1700
Data Index: 119632 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9148. Min Range: -4.9148
Max Act: 4.5711. Min Act: -0.1700
Data Index: 4526069 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19