Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5204 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.6723. Min Act: -0.1700
Data Index: 6702500 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.7036. Min Act: -0.1700
Data Index: 2235705 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.4223. Min Act: -0.1700
Data Index: 5880212 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.3598. Min Act: -0.1700
Data Index: 6078670 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.3286. Min Act: -0.1700
Data Index: 2214977 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.2973. Min Act: -0.1700
Data Index: 7917133 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.2661. Min Act: -0.1700
Data Index: 5524744 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.2348. Min Act: -0.1700
Data Index: 1521183 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.1723. Min Act: -0.1700
Data Index: 6496305 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.1098. Min Act: -0.1700
Data Index: 4183391 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.1098. Min Act: -0.1700
Data Index: 1503549 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.1098. Min Act: -0.1700
Data Index: 5720148 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.1098. Min Act: -0.1700
Data Index: 8776780 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.1098. Min Act: -0.1700
Data Index: 7225166 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.1098. Min Act: -0.1700
Data Index: 752103 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.1098. Min Act: -0.1700
Data Index: 4591355 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.1098. Min Act: -0.1700
Data Index: 5404897 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.0786. Min Act: -0.1700
Data Index: 3961588 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.0786. Min Act: -0.1700
Data Index: 4236287 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.0786. Min Act: -0.1700
Data Index: 3098105 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19