Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4958 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.6201. Min Act: -0.1700
Data Index: 2642689 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.5264. Min Act: -0.1700
Data Index: 743158 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.4951. Min Act: -0.1700
Data Index: 7169987 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.4326. Min Act: -0.1700
Data Index: 5993537 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.4326. Min Act: -0.1700
Data Index: 6671194 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.4326. Min Act: -0.1700
Data Index: 1537656 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.4014. Min Act: -0.1700
Data Index: 6489497 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3389. Min Act: -0.1700
Data Index: 7700567 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.4014. Min Act: -0.1700
Data Index: 3973769 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3701. Min Act: -0.1700
Data Index: 3374469 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3389. Min Act: -0.1700
Data Index: 5296049 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3076. Min Act: -0.1700
Data Index: 790194 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3389. Min Act: -0.1700
Data Index: 4347331 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3076. Min Act: -0.1700
Data Index: 660080 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3076. Min Act: -0.1700
Data Index: 1671498 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3076. Min Act: -0.1700
Data Index: 776105 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3076. Min Act: -0.1700
Data Index: 4833024 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3076. Min Act: -0.1700
Data Index: 2868741 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3076. Min Act: -0.1700
Data Index: 4427326 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6201. Min Range: -5.6201
Max Act: 5.3076. Min Act: -0.1700
Data Index: 1469694 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19