Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2029. Min Range: -11.2029
Max Act: 11.2029. Min Act: -0.1700
Data Index: 7484023 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.8904. Min Act: -0.1700
Data Index: 355570 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.8279. Min Act: -0.1700
Data Index: 8210730 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.8279. Min Act: -0.1700
Data Index: 6141623 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.5779. Min Act: -0.1700
Data Index: 4630976 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.5779. Min Act: -0.1700
Data Index: 8176908 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.5154. Min Act: -0.1700
Data Index: 4478903 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.4529. Min Act: -0.1700
Data Index: 5073560 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.4529. Min Act: -0.1700
Data Index: 4129984 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.4529. Min Act: -0.1700
Data Index: 945173 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.3279. Min Act: -0.1700
Data Index: 6314316 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.3904. Min Act: -0.1700
Data Index: 6944388 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.3279. Min Act: -0.1700
Data Index: 2287536 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.2654. Min Act: -0.1700
Data Index: 5861635 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.2654. Min Act: -0.1700
Data Index: 4070055 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.2029. Min Act: -0.1700
Data Index: 3422481 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.2029. Min Act: -0.1700
Data Index: 1053085 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.2029. Min Act: -0.1700
Data Index: 1491544 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.0779. Min Act: -0.1700
Data Index: 6180254 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2029. Min Range: -11.2029
Max Act: 10.0779. Min Act: -0.1700
Data Index: 3045361 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19