Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.6554. Min Act: -0.1700
Data Index: 779211 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.5304. Min Act: -0.1700
Data Index: 3686297 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4992. Min Act: -0.1700
Data Index: 6431961 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4679. Min Act: -0.1700
Data Index: 6608402 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4054. Min Act: -0.1700
Data Index: 5075771 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.3742. Min Act: -0.1700
Data Index: 1546640 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4054. Min Act: -0.1700
Data Index: 7476426 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.4054. Min Act: -0.1700
Data Index: 4156733 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.3742. Min Act: -0.1700
Data Index: 6115795 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.3429. Min Act: -0.1700
Data Index: 3949105 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.3742. Min Act: -0.1700
Data Index: 659280 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.3117. Min Act: -0.1700
Data Index: 1333890 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.2804. Min Act: -0.1700
Data Index: 4243903 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.2804. Min Act: -0.1700
Data Index: 7708106 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.3117. Min Act: -0.1700
Data Index: 779212 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.2804. Min Act: -0.1700
Data Index: 2629826 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.2804. Min Act: -0.1700
Data Index: 1020327 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.2492. Min Act: -0.1700
Data Index: 1546639 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.2179. Min Act: -0.1700
Data Index: 3209362 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6554. Min Range: -5.6554
Max Act: 5.2179. Min Act: -0.1700
Data Index: 4031889 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19