Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 562 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.7280. Min Act: -0.1700
Data Index: 991455 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.6640. Min Act: -0.1700
Data Index: 1781141 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.6158. Min Act: -0.1700
Data Index: 5234000 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5997. Min Act: -0.1700
Data Index: 4998877 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5997. Min Act: -0.1700
Data Index: 4370663 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5997. Min Act: -0.1700
Data Index: 869511 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5836. Min Act: -0.1700
Data Index: 2546182 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5836. Min Act: -0.1700
Data Index: 2643507 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5675. Min Act: -0.1700
Data Index: 5687900 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5836. Min Act: -0.1700
Data Index: 1919378 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5836. Min Act: -0.1700
Data Index: 3350417 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5514. Min Act: -0.1700
Data Index: 3567630 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5352. Min Act: -0.1700
Data Index: 4267742 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5514. Min Act: -0.1700
Data Index: 6954913 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5191. Min Act: -0.1700
Data Index: 8282824 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5352. Min Act: -0.1700
Data Index: 4303545 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5352. Min Act: -0.1700
Data Index: 7075506 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5352. Min Act: -0.1700
Data Index: 7690758 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5352. Min Act: -0.1700
Data Index: 3223310 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5191. Min Act: -0.1700
Data Index: 1606820 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19