Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.9801. Min Act: -0.1700
Data Index: 4288878 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.9489. Min Act: -0.1700
Data Index: 4392374 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.8551. Min Act: -0.1700
Data Index: 3981474 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.8238. Min Act: -0.1700
Data Index: 934589 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.8238. Min Act: -0.1700
Data Index: 1538019 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.8238. Min Act: -0.1700
Data Index: 2676777 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.7925. Min Act: -0.1700
Data Index: 4415354 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.7613. Min Act: -0.1700
Data Index: 5292145 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.7300. Min Act: -0.1700
Data Index: 3871739 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.7613. Min Act: -0.1700
Data Index: 5254977 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.7300. Min Act: -0.1700
Data Index: 5676701 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.7613. Min Act: -0.1700
Data Index: 5628191 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.7300. Min Act: -0.1700
Data Index: 3508249 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.7143. Min Act: -0.1700
Data Index: 4443985 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.7143. Min Act: -0.1700
Data Index: 6577144 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.7143. Min Act: -0.1700
Data Index: 2621243 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.6987. Min Act: -0.1700
Data Index: 3048377 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.6987. Min Act: -0.1700
Data Index: 5285692 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.6987. Min Act: -0.1700
Data Index: 201508 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9801. Min Range: -3.9801
Max Act: 3.6830. Min Act: -0.1700
Data Index: 5211347 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19