Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5079. Min Range: -7.5079
Max Act: 7.5079. Min Act: -0.1700
Data Index: 4376856 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5079. Min Range: -7.5079
Max Act: 7.2267. Min Act: -0.1700
Data Index: 2047258 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5079. Min Range: -7.5079
Max Act: 7.2267. Min Act: -0.1700
Data Index: 850081 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5079. Min Range: -7.5079
Max Act: 7.0392. Min Act: -0.1700
Data Index: 6991092 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.9767. Min Act: -0.1700
Data Index: 2065285 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.9454. Min Act: -0.1700
Data Index: 5763316 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.9142. Min Act: -0.1700
Data Index: 6662521 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.8829. Min Act: -0.1700
Data Index: 3860017 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.8829. Min Act: -0.1700
Data Index: 8699945 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.8204. Min Act: -0.1700
Data Index: 6788727 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.8204. Min Act: -0.1700
Data Index: 5655579 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.8204. Min Act: -0.1700
Data Index: 3546467 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.7892. Min Act: -0.1700
Data Index: 650711 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.7579. Min Act: -0.1700
Data Index: 271811 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.7579. Min Act: -0.1700
Data Index: 6250167 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.7579. Min Act: -0.1700
Data Index: 7932793 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.6642. Min Act: -0.1700
Data Index: 5888176 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.6642. Min Act: -0.1700
Data Index: 5446053 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.6954. Min Act: -0.1700
Data Index: 2729964 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5079. Min Range: -7.5079
Max Act: 6.6642. Min Act: -0.1700
Data Index: 5929390 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19