Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4693 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5066. Min Range: -7.5066
Max Act: 7.5066. Min Act: -0.1700
Data Index: 2341030 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5066. Min Range: -7.5066
Max Act: 7.0691. Min Act: -0.1700
Data Index: 42783 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5066. Min Range: -7.5066
Max Act: 7.0691. Min Act: -0.1700
Data Index: 631094 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5066. Min Range: -7.5066
Max Act: 7.0378. Min Act: -0.1700
Data Index: 2013811 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.9753. Min Act: -0.1700
Data Index: 5017394 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.9128. Min Act: -0.1700
Data Index: 1604218 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.9441. Min Act: -0.1700
Data Index: 3998314 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.9441. Min Act: -0.1700
Data Index: 989291 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.9441. Min Act: -0.1700
Data Index: 1323623 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.9128. Min Act: -0.1700
Data Index: 4082537 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.9128. Min Act: -0.1700
Data Index: 7380470 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.9128. Min Act: -0.1700
Data Index: 6062493 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.9128. Min Act: -0.1700
Data Index: 294123 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.8503. Min Act: -0.1700
Data Index: 1446386 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.8816. Min Act: -0.1700
Data Index: 4722890 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.8191. Min Act: -0.1700
Data Index: 3095000 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.8191. Min Act: -0.1700
Data Index: 203319 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.7878. Min Act: -0.1700
Data Index: 1185846 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.8191. Min Act: -0.1700
Data Index: 5222597 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5066. Min Range: -7.5066
Max Act: 6.8191. Min Act: -0.1700
Data Index: 3060468 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19