Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1939 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.9452. Min Act: -0.1699
Data Index: 3134991 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.8515. Min Act: -0.1700
Data Index: 997403 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.7577. Min Act: -0.1700
Data Index: 8051060 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.6640. Min Act: -0.1700
Data Index: 833397 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.6015. Min Act: -0.1700
Data Index: 2840084 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.6327. Min Act: -0.1700
Data Index: 1600641 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.6327. Min Act: -0.1700
Data Index: 4313828 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.5077. Min Act: -0.1700
Data Index: 448697 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.4452. Min Act: -0.1700
Data Index: 2292329 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.3983. Min Act: -0.1700
Data Index: 3278961 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.4608. Min Act: -0.1700
Data Index: 1480341 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.3983. Min Act: -0.1700
Data Index: 857834 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.3671. Min Act: -0.1700
Data Index: 4074516 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.3202. Min Act: -0.1700
Data Index: 66848 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.3202. Min Act: -0.1699
Data Index: 6460615 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.3046. Min Act: -0.1700
Data Index: 435575 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.2733. Min Act: -0.1700
Data Index: 6690412 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.2577. Min Act: -0.1700
Data Index: 833097 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.2733. Min Act: -0.1700
Data Index: 562572 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9452. Min Range: -5.9452
Max Act: 5.2733. Min Act: -0.1700
Data Index: 734242 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19