Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1661 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.3627. Min Act: -0.1700
Data Index: 218185 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.3463. Min Act: -0.1700
Data Index: 2019382 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.3463. Min Act: -0.1700
Data Index: 7060765 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2805. Min Act: -0.1700
Data Index: 8705299 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2970. Min Act: -0.1700
Data Index: 6147336 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2970. Min Act: -0.1700
Data Index: 5033978 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2805. Min Act: -0.1700
Data Index: 4047856 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2805. Min Act: -0.1700
Data Index: 1294926 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2805. Min Act: -0.1700
Data Index: 3562815 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2640. Min Act: -0.1700
Data Index: 8146393 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2640. Min Act: -0.1700
Data Index: 2016119 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2475. Min Act: -0.1700
Data Index: 6813168 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2310. Min Act: -0.1700
Data Index: 3211168 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2475. Min Act: -0.1700
Data Index: 7157394 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2475. Min Act: -0.1700
Data Index: 6844479 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2475. Min Act: -0.1700
Data Index: 4568829 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2475. Min Act: -0.1700
Data Index: 4336120 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2475. Min Act: -0.1700
Data Index: 3625736 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2475. Min Act: -0.1700
Data Index: 630874 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3627. Min Range: -2.3627
Max Act: 2.2640. Min Act: -0.1700
Data Index: 8141956 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19