Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2175 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.4405. Min Act: -0.1700
Data Index: 2166546 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.4249. Min Act: -0.1700
Data Index: 6158960 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.4405. Min Act: -0.1700
Data Index: 5933295 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.4249. Min Act: -0.1700
Data Index: 4356604 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.4249. Min Act: -0.1700
Data Index: 141680 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3935. Min Act: -0.1700
Data Index: 1994671 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3778. Min Act: -0.1700
Data Index: 987198 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3778. Min Act: -0.1700
Data Index: 550228 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3778. Min Act: -0.1700
Data Index: 5696684 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3778. Min Act: -0.1700
Data Index: 8403889 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3621. Min Act: -0.1700
Data Index: 6109980 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3621. Min Act: -0.1700
Data Index: 504248 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3621. Min Act: -0.1700
Data Index: 2511439 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3465. Min Act: -0.1700
Data Index: 8218787 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3308. Min Act: -0.1700
Data Index: 8442574 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3151. Min Act: -0.1700
Data Index: 3994706 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3151. Min Act: -0.1700
Data Index: 1719662 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2837. Min Act: -0.1700
Data Index: 2255144 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2994. Min Act: -0.1700
Data Index: 3679971 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2680. Min Act: -0.1700
Data Index: 2185578 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19