Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2301 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.5940. Min Act: -0.1700
Data Index: 7122138 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.5314. Min Act: -0.1700
Data Index: 1058293 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.5157. Min Act: -0.1700
Data Index: 135340 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.5001. Min Act: -0.1700
Data Index: 4069369 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.5001. Min Act: -0.1700
Data Index: 4245313 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.4531. Min Act: -0.1700
Data Index: 3465755 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.4217. Min Act: -0.1700
Data Index: 5094184 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.4217. Min Act: -0.1700
Data Index: 3862319 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.4374. Min Act: -0.1700
Data Index: 8364491 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.4217. Min Act: -0.1700
Data Index: 7875751 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.4060. Min Act: -0.1700
Data Index: 5984897 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.4060. Min Act: -0.1700
Data Index: 2815098 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.3904. Min Act: -0.1700
Data Index: 4038070 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.3904. Min Act: -0.1700
Data Index: 5501295 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.4060. Min Act: -0.1700
Data Index: 84278 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.4060. Min Act: -0.1700
Data Index: 4268405 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.3747. Min Act: -0.1700
Data Index: 8607247 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.3590. Min Act: -0.1700
Data Index: 287324 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.3590. Min Act: -0.1700
Data Index: 7860293 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5940. Min Range: -3.5940
Max Act: 3.3747. Min Act: -0.1700
Data Index: 3374409 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19