Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2475 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0997. Min Act: -0.1700
Data Index: 2577759 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.1310. Min Act: -0.1700
Data Index: 806678 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0372. Min Act: -0.1700
Data Index: 7137343 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0060. Min Act: -0.1697
Data Index: 7137342 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9747. Min Act: -0.1700
Data Index: 3151789 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9747. Min Act: -0.1700
Data Index: 1844289 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0060. Min Act: -0.1700
Data Index: 5220216 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9747. Min Act: -0.1700
Data Index: 4528848 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 5317173 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9747. Min Act: -0.1700
Data Index: 7421932 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9747. Min Act: -0.1700
Data Index: 7783045 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9122. Min Act: -0.1700
Data Index: 4892534 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9747. Min Act: -0.1700
Data Index: 4892531 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 6916057 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9747. Min Act: -0.1700
Data Index: 8304685 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1699
Data Index: 6054019 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 4312405 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 120123 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 5078744 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9122. Min Act: -0.1700
Data Index: 3804049 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19