Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4569 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.7202. Min Act: -0.1700
Data Index: 6418839 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.5640. Min Act: -0.1700
Data Index: 3625350 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.4390. Min Act: -0.1700
Data Index: 6741316 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.4702. Min Act: -0.1700
Data Index: 2377078 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.4390. Min Act: -0.1700
Data Index: 7376778 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.4077. Min Act: -0.1700
Data Index: 1562196 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.4077. Min Act: -0.1700
Data Index: 6364563 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.3765. Min Act: -0.1700
Data Index: 1104021 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.3765. Min Act: -0.1700
Data Index: 6712997 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.3140. Min Act: -0.1700
Data Index: 4872057 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.2827. Min Act: -0.1700
Data Index: 6302347 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.2515. Min Act: -0.1700
Data Index: 2377076 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.2515. Min Act: -0.1700
Data Index: 4872059 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.2515. Min Act: -0.1700
Data Index: 4414075 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.2515. Min Act: -0.1700
Data Index: 5307988 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.2515. Min Act: -0.1700
Data Index: 3590512 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.2202. Min Act: -0.1700
Data Index: 7186513 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.2202. Min Act: -0.1700
Data Index: 7400578 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.1577. Min Act: -0.1700
Data Index: 7126223 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7202. Min Range: -5.7202
Max Act: 5.1577. Min Act: -0.1700
Data Index: 40078 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19