Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3571 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0529. Min Range: -7.0529
Max Act: 7.0529. Min Act: -0.1700
Data Index: 7146706 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.8967. Min Act: -0.1700
Data Index: 7106354 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.8342. Min Act: -0.1700
Data Index: 4251014 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.8029. Min Act: -0.1700
Data Index: 4182567 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.7717. Min Act: -0.1700
Data Index: 8687039 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.7404. Min Act: -0.1700
Data Index: 4735198 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.7404. Min Act: -0.1700
Data Index: 8158695 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.7404. Min Act: -0.1700
Data Index: 769265 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.7092. Min Act: -0.1700
Data Index: 7463764 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.7092. Min Act: -0.1700
Data Index: 802915 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.6779. Min Act: -0.1700
Data Index: 2112787 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.7092. Min Act: -0.1700
Data Index: 909418 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.6779. Min Act: -0.1700
Data Index: 4703657 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.6467. Min Act: -0.1700
Data Index: 6718146 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.6467. Min Act: -0.1700
Data Index: 7373931 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.6467. Min Act: -0.1700
Data Index: 1131261 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.6467. Min Act: -0.1700
Data Index: 4201094 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.6154. Min Act: -0.1700
Data Index: 1158048 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.5842. Min Act: -0.1700
Data Index: 5217757 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0529. Min Range: -7.0529
Max Act: 6.6154. Min Act: -0.1700
Data Index: 233102 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19