Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.1310. Min Act: -0.1700
Data Index: 2090771 (Open Web Text)
Max Activating Token Index: 670
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: 8707951 (Open Web Text)
Max Activating Token Index: 563
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: 6647587 (Open Web Text)
Max Activating Token Index: 313
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: -0.1700
Data Index: 8538148 (Open Web Text)
Max Activating Token Index: 237
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: 777704 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 6034815 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 3316594 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 7750490 (Open Web Text)
Max Activating Token Index: 932
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: 6322517 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 4345862 (Open Web Text)
Max Activating Token Index: 436
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: 8827543 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 1614820 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9122. Min Act: -0.1700
Data Index: 129146 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 1839631 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 7694930 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9122. Min Act: -0.1700
Data Index: 4838113 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9122. Min Act: -0.1700
Data Index: 5198517 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 1416710 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8497. Min Act: -0.1700
Data Index: 6947915 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8497. Min Act: -0.1700
Data Index: 2711129 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19