Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.6622. Min Act: -0.1700
Data Index: 3775099 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.6465. Min Act: -0.1700
Data Index: 1538550 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.5996. Min Act: -0.1700
Data Index: 7819798 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.5369. Min Act: -0.1700
Data Index: 2445351 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.5213. Min Act: -0.1700
Data Index: 5596351 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.5213. Min Act: -0.1700
Data Index: 5581088 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.5056. Min Act: -0.1700
Data Index: 7133697 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4743. Min Act: -0.1700
Data Index: 6185754 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4743. Min Act: -0.1700
Data Index: 7633772 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4743. Min Act: -0.1700
Data Index: 674279 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4743. Min Act: -0.1700
Data Index: 6678318 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4586. Min Act: -0.1700
Data Index: 6869878 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4586. Min Act: -0.1700
Data Index: 7650695 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4430. Min Act: -0.1700
Data Index: 742245 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4273. Min Act: -0.1700
Data Index: 580838 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4273. Min Act: -0.1700
Data Index: 2777973 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4116. Min Act: -0.1700
Data Index: 1008895 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4273. Min Act: -0.1700
Data Index: 1456608 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4273. Min Act: -0.1700
Data Index: 7143555 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6622. Min Range: -3.6622
Max Act: 3.4273. Min Act: -0.1700
Data Index: 4276383 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19