Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4754 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.5522. Min Act: -0.1700
Data Index: 3421878 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.5366. Min Act: -0.1700
Data Index: 3062373 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.5053. Min Act: -0.1700
Data Index: 676541 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4896. Min Act: -0.1700
Data Index: 7815622 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4896. Min Act: -0.1700
Data Index: 7461165 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4426. Min Act: -0.1700
Data Index: 4277081 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4426. Min Act: -0.1700
Data Index: 4181610 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4426. Min Act: -0.1700
Data Index: 7815620 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4426. Min Act: -0.1700
Data Index: 6396873 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4269. Min Act: -0.1700
Data Index: 5839322 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4269. Min Act: -0.1700
Data Index: 4482129 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4426. Min Act: -0.1700
Data Index: 7274991 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4426. Min Act: -0.1700
Data Index: 269212 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4269. Min Act: -0.1700
Data Index: 7140777 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4112. Min Act: -0.1700
Data Index: 6042399 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4112. Min Act: -0.1700
Data Index: 676587 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3956. Min Act: -0.1700
Data Index: 1396212 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4112. Min Act: -0.1700
Data Index: 578011 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4112. Min Act: -0.1700
Data Index: 7109721 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3799. Min Act: -0.1700
Data Index: 5045571 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19