Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2541 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.6405. Min Act: -0.1700
Data Index: 7211904 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.6405. Min Act: -0.1700
Data Index: 97915 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.5468. Min Act: -0.1700
Data Index: 7780329 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.5155. Min Act: -0.1700
Data Index: 2851623 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.4530. Min Act: -0.1700
Data Index: 544763 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.4218. Min Act: -0.1700
Data Index: 2940960 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.4218. Min Act: -0.1700
Data Index: 5829149 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.3905. Min Act: -0.1700
Data Index: 1380541 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.3905. Min Act: -0.1700
Data Index: 5827232 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.3905. Min Act: -0.1700
Data Index: 5190621 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.3280. Min Act: -0.1700
Data Index: 7900607 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.3280. Min Act: -0.1700
Data Index: 4991674 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.3280. Min Act: -0.1700
Data Index: 2257501 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.3280. Min Act: -0.1700
Data Index: 4932303 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.2968. Min Act: -0.1700
Data Index: 7826503 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.2968. Min Act: -0.1700
Data Index: 7201983 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.2655. Min Act: -0.1700
Data Index: 7558641 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.2655. Min Act: -0.1700
Data Index: 6286026 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.2655. Min Act: -0.1700
Data Index: 4593525 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6405. Min Range: -5.6405
Max Act: 5.2655. Min Act: -0.1700
Data Index: 3764424 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19