Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.5080. Min Act: -0.1700
Data Index: 6562606 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.2267. Min Act: -0.1700
Data Index: 2945404 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.2267. Min Act: -0.1700
Data Index: 7750113 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.2267. Min Act: -0.1700
Data Index: 2150047 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.2267. Min Act: -0.1700
Data Index: 1179130 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.1955. Min Act: -0.1700
Data Index: 6876946 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.1642. Min Act: -0.1700
Data Index: 5985567 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.1642. Min Act: -0.1700
Data Index: 8093002 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.1017. Min Act: -0.1700
Data Index: 3731574 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.0705. Min Act: -0.1700
Data Index: 2859766 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.0705. Min Act: -0.1700
Data Index: 188589 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.0392. Min Act: -0.1700
Data Index: 1255661 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.0392. Min Act: -0.1700
Data Index: 433937 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.0392. Min Act: -0.1700
Data Index: 5922013 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.0080. Min Act: -0.1700
Data Index: 1552656 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5080. Min Range: -6.5080
Max Act: 6.0080. Min Act: -0.1700
Data Index: 5884064 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5080. Min Range: -6.5080
Max Act: 5.9142. Min Act: -0.1700
Data Index: 5169023 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5080. Min Range: -6.5080
Max Act: 5.9142. Min Act: -0.1700
Data Index: 227457 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5080. Min Range: -6.5080
Max Act: 5.9142. Min Act: -0.1700
Data Index: 6878613 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5080. Min Range: -6.5080
Max Act: 5.8830. Min Act: -0.1700
Data Index: 5489616 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19