Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1906 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.8620. Min Act: -0.1700
Data Index: 8337493 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.8308. Min Act: -0.1700
Data Index: 3400391 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.7995. Min Act: -0.1700
Data Index: 7561680 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.7058. Min Act: -0.1700
Data Index: 6789041 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.7058. Min Act: -0.1700
Data Index: 3542567 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.6745. Min Act: -0.1700
Data Index: 4347785 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.6745. Min Act: -0.1700
Data Index: 8765980 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.6745. Min Act: -0.1700
Data Index: 7500412 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.6745. Min Act: -0.1700
Data Index: 4239444 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.6745. Min Act: -0.1700
Data Index: 7776412 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.6433. Min Act: -0.1700
Data Index: 3546226 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.6120. Min Act: -0.1700
Data Index: 41068 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.6120. Min Act: -0.1700
Data Index: 8732275 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.6120. Min Act: -0.1700
Data Index: 86835 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.5808. Min Act: -0.1700
Data Index: 7987068 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.5808. Min Act: -0.1700
Data Index: 2688850 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.5808. Min Act: -0.1700
Data Index: 8782854 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.5808. Min Act: -0.1700
Data Index: 152218 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.5808. Min Act: -0.1700
Data Index: 6277435 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8620. Min Range: -5.8620
Max Act: 5.5495. Min Act: -0.1700
Data Index: 1309618 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19