Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3116 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1172. Min Range: -7.1172
Max Act: 7.1172. Min Act: -0.1700
Data Index: 7919805 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1172. Min Range: -7.1172
Max Act: 7.0547. Min Act: -0.1700
Data Index: 3335970 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1172. Min Range: -7.1172
Max Act: 7.0234. Min Act: -0.1700
Data Index: 4669679 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.9609. Min Act: -0.1700
Data Index: 8260577 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.8672. Min Act: -0.1700
Data Index: 2977342 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.8672. Min Act: -0.1700
Data Index: 3860355 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.8359. Min Act: -0.1700
Data Index: 8704498 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.8047. Min Act: -0.1700
Data Index: 65791 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.7734. Min Act: -0.1700
Data Index: 8682455 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.7734. Min Act: -0.1700
Data Index: 1061634 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.7734. Min Act: -0.1700
Data Index: 7041890 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.7422. Min Act: -0.1700
Data Index: 6818405 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.7422. Min Act: -0.1700
Data Index: 6909304 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.7422. Min Act: -0.1700
Data Index: 7470475 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.7109. Min Act: -0.1700
Data Index: 405917 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.6797. Min Act: -0.1700
Data Index: 1943364 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.6797. Min Act: -0.1700
Data Index: 8331410 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.6484. Min Act: -0.1700
Data Index: 8477530 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.6484. Min Act: -0.1700
Data Index: 4518755 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1172. Min Range: -7.1172
Max Act: 6.6172. Min Act: -0.1700
Data Index: 8299773 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19