Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.2266. Min Act: -0.1700
Data Index: 3911867 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.2266. Min Act: -0.1700
Data Index: 7215970 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.1016. Min Act: -0.1700
Data Index: 3810945 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.1016. Min Act: -0.1700
Data Index: 1288182 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0703. Min Act: -0.1700
Data Index: 5775210 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0703. Min Act: -0.1700
Data Index: 3926481 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0703. Min Act: -0.1700
Data Index: 7421715 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0703. Min Act: -0.1700
Data Index: 3926480 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0703. Min Act: -0.1700
Data Index: 4084523 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0391. Min Act: -0.1700
Data Index: 3270367 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0391. Min Act: -0.1700
Data Index: 1639612 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0391. Min Act: -0.1700
Data Index: 8644722 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0391. Min Act: -0.1700
Data Index: 2459579 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0391. Min Act: -0.1700
Data Index: 144222 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0078. Min Act: -0.1700
Data Index: 2930972 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2266. Min Range: -5.2266
Max Act: 5.0078. Min Act: -0.1700
Data Index: 4606528 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.9766. Min Act: -0.1700
Data Index: 5305719 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.9766. Min Act: -0.1700
Data Index: 4428036 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.9766. Min Act: -0.1700
Data Index: 2684485 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2266. Min Range: -5.2266
Max Act: 4.9766. Min Act: -0.1700
Data Index: 4511035 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19