Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3302 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.3594. Min Act: -0.1700
Data Index: 4326555 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.3124. Min Act: -0.1700
Data Index: 410518 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2810. Min Act: -0.1700
Data Index: 3002541 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2495. Min Act: -0.1700
Data Index: 7634860 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2338. Min Act: -0.1700
Data Index: 6492214 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2338. Min Act: -0.1700
Data Index: 5304055 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2181. Min Act: -0.1700
Data Index: 6370550 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2338. Min Act: -0.1700
Data Index: 8267324 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2181. Min Act: -0.1700
Data Index: 2574341 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2181. Min Act: -0.1700
Data Index: 2786112 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2024. Min Act: -0.1700
Data Index: 991184 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2024. Min Act: -0.1700
Data Index: 8658741 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2181. Min Act: -0.1700
Data Index: 7197863 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.2024. Min Act: -0.1700
Data Index: 2894550 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.1867. Min Act: -0.1700
Data Index: 3451513 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.1394. Min Act: -0.1700
Data Index: 3761962 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.1394. Min Act: -0.1700
Data Index: 4877274 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.1394. Min Act: -0.1700
Data Index: 3465363 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.1394. Min Act: -0.1700
Data Index: 5385075 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3594. Min Range: -3.3594
Max Act: 3.1394. Min Act: -0.1700
Data Index: 1041576 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19