Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.9142. Min Act: -0.1700
Data Index: 2897832 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.7578. Min Act: -0.1700
Data Index: 847783 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.7422. Min Act: -0.1700
Data Index: 8298931 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.6640. Min Act: -0.1700
Data Index: 1510042 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.6327. Min Act: -0.1700
Data Index: 4357484 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.6170. Min Act: -0.1700
Data Index: 5331223 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.5857. Min Act: -0.1700
Data Index: 7091622 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.5857. Min Act: -0.1700
Data Index: 6160987 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.5701. Min Act: -0.1700
Data Index: 6480502 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.5857. Min Act: -0.1700
Data Index: 6019978 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.5544. Min Act: -0.1700
Data Index: 4626652 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.5231. Min Act: -0.1700
Data Index: 2429175 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.4918. Min Act: -0.1700
Data Index: 6160993 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.5074. Min Act: -0.1700
Data Index: 3801661 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.4604. Min Act: -0.1700
Data Index: 7116009 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.4918. Min Act: -0.1700
Data Index: 4355858 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.4761. Min Act: -0.1700
Data Index: 8032167 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.4761. Min Act: -0.1700
Data Index: 8107936 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.4761. Min Act: -0.1700
Data Index: 5885596 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9142. Min Range: -3.9142
Max Act: 3.4604. Min Act: -0.1700
Data Index: 2843820 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19