Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 312 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.9450. Min Act: -0.1700
Data Index: 5866694 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.9137. Min Act: -0.1700
Data Index: 1015880 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.8825. Min Act: -0.1700
Data Index: 1015882 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.8512. Min Act: -0.1700
Data Index: 1015879 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.8200. Min Act: -0.1700
Data Index: 4448172 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.7575. Min Act: -0.1700
Data Index: 7456094 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.7262. Min Act: -0.1700
Data Index: 1015881 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.6325. Min Act: -0.1700
Data Index: 4448175 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.6325. Min Act: -0.1700
Data Index: 7907967 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.6325. Min Act: -0.1700
Data Index: 2522360 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.6012. Min Act: -0.1700
Data Index: 4844255 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.6012. Min Act: -0.1700
Data Index: 6947424 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.6325. Min Act: -0.1700
Data Index: 3245150 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.5700. Min Act: -0.1700
Data Index: 6947416 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.5075. Min Act: -0.1700
Data Index: 6947417 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.5075. Min Act: -0.1700
Data Index: 7001612 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.4762. Min Act: -0.1700
Data Index: 4844257 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.4762. Min Act: -0.1700
Data Index: 2286662 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.4450. Min Act: -0.1700
Data Index: 6174991 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9450. Min Range: -5.9450
Max Act: 5.4762. Min Act: -0.1700
Data Index: 5414832 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19