Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2160 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.4941. Min Act: -0.1700
Data Index: 949578 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.4941. Min Act: -0.1700
Data Index: 1075900 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.4316. Min Act: -0.1700
Data Index: 5067107 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.4316. Min Act: -0.1700
Data Index: 4773850 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.4004. Min Act: -0.1700
Data Index: 4976658 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.4004. Min Act: -0.1700
Data Index: 1703620 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.4004. Min Act: -0.1700
Data Index: 6850865 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.4004. Min Act: -0.1700
Data Index: 1131520 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.3691. Min Act: -0.1700
Data Index: 7381143 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.3691. Min Act: -0.1700
Data Index: 4153935 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.2753. Min Act: -0.1700
Data Index: 8271774 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.3066. Min Act: -0.1700
Data Index: 4506338 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.2753. Min Act: -0.1700
Data Index: 7013762 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.2753. Min Act: -0.1700
Data Index: 695536 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.2753. Min Act: -0.1700
Data Index: 6574144 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.2441. Min Act: -0.1700
Data Index: 1753274 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.2753. Min Act: -0.1700
Data Index: 1944104 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.2753. Min Act: -0.1700
Data Index: 5824672 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.2753. Min Act: -0.1700
Data Index: 2069830 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4941. Min Range: -4.4941
Max Act: 4.2441. Min Act: -0.1700
Data Index: 1306118 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19