Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.9610. Min Act: -0.1700
Data Index: 2048446 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.9298. Min Act: -0.1700
Data Index: 7202340 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.8985. Min Act: -0.1700
Data Index: 5807434 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.8360. Min Act: -0.1700
Data Index: 4060999 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.8360. Min Act: -0.1700
Data Index: 4767481 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.8673. Min Act: -0.1700
Data Index: 6013234 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7735. Min Act: -0.1700
Data Index: 796662 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.8048. Min Act: -0.1700
Data Index: 2634053 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.8048. Min Act: -0.1700
Data Index: 1472821 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.8048. Min Act: -0.1700
Data Index: 347352 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.8048. Min Act: -0.1700
Data Index: 6483859 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.8048. Min Act: -0.1700
Data Index: 5777937 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7735. Min Act: -0.1700
Data Index: 4543842 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7735. Min Act: -0.1700
Data Index: 5723931 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7423. Min Act: -0.1700
Data Index: 7870769 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7735. Min Act: -0.1700
Data Index: 8789361 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7423. Min Act: -0.1700
Data Index: 6790702 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7423. Min Act: -0.1700
Data Index: 750789 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7735. Min Act: -0.1700
Data Index: 2339241 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9610. Min Range: -5.9610
Max Act: 5.7423. Min Act: -0.1700
Data Index: 1286234 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19