Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.2119. Min Act: -0.1700
Data Index: 135444 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.1807. Min Act: -0.1700
Data Index: 7654368 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.1807. Min Act: -0.1700
Data Index: 2947306 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.2119. Min Act: -0.1700
Data Index: 7050557 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.1494. Min Act: -0.1700
Data Index: 483159 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.1494. Min Act: -0.1700
Data Index: 5733369 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.1494. Min Act: -0.1700
Data Index: 3050514 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.1494. Min Act: -0.1700
Data Index: 6339809 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.0869. Min Act: -0.1700
Data Index: 1202011 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.1494. Min Act: -0.1700
Data Index: 2868164 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.1182. Min Act: -0.1700
Data Index: 1689990 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.0869. Min Act: -0.1700
Data Index: 297829 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.0869. Min Act: -0.1700
Data Index: 1970518 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.0557. Min Act: -0.1700
Data Index: 4361345 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.0244. Min Act: -0.1700
Data Index: 6386524 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2119. Min Range: -5.2119
Max Act: 5.0244. Min Act: -0.1700
Data Index: 385937 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2119. Min Range: -5.2119
Max Act: 4.9932. Min Act: -0.1700
Data Index: 3642718 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2119. Min Range: -5.2119
Max Act: 4.9932. Min Act: -0.1700
Data Index: 912587 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2119. Min Range: -5.2119
Max Act: 4.9619. Min Act: -0.1700
Data Index: 34964 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2119. Min Range: -5.2119
Max Act: 4.9932. Min Act: -0.1700
Data Index: 665132 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19