Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2223 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.9739. Min Act: -0.1700
Data Index: 3409647 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.8947. Min Act: -0.1700
Data Index: 205057 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.8470. Min Act: -0.1700
Data Index: 5906478 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.8470. Min Act: -0.1700
Data Index: 7823273 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7993. Min Act: -0.1700
Data Index: 5164259 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7993. Min Act: -0.1700
Data Index: 1072147 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7674. Min Act: -0.1700
Data Index: 1613480 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7674. Min Act: -0.1700
Data Index: 4028977 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7674. Min Act: -0.1700
Data Index: 4243158 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7674. Min Act: -0.1700
Data Index: 8400436 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7834. Min Act: -0.1700
Data Index: 6889884 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7515. Min Act: -0.1700
Data Index: 3584483 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7515. Min Act: -0.1700
Data Index: 4137093 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7355. Min Act: -0.1700
Data Index: 8752723 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7355. Min Act: -0.1700
Data Index: 347629 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7355. Min Act: -0.1700
Data Index: 4588325 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7355. Min Act: -0.1700
Data Index: 6234981 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7195. Min Act: -0.1700
Data Index: 5529608 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7355. Min Act: -0.1700
Data Index: 323844 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9739. Min Range: -2.9739
Max Act: 2.7035. Min Act: -0.1700
Data Index: 4029448 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19