Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1422. Min Range: -5.1422
Max Act: 5.1422. Min Act: -0.1700
Data Index: 1595735 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1422. Min Range: -5.1422
Max Act: 5.0797. Min Act: -0.1700
Data Index: 1035265 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1422. Min Range: -5.1422
Max Act: 5.0797. Min Act: -0.1700
Data Index: 4848630 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1422. Min Range: -5.1422
Max Act: 5.0797. Min Act: -0.1700
Data Index: 6710507 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1422. Min Range: -5.1422
Max Act: 5.0485. Min Act: -0.1700
Data Index: 7183833 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1422. Min Range: -5.1422
Max Act: 5.0485. Min Act: -0.1700
Data Index: 946136 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.9859. Min Act: -0.1700
Data Index: 6506208 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.9859. Min Act: -0.1700
Data Index: 7400659 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.9547. Min Act: -0.1700
Data Index: 3750602 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1422. Min Range: -5.1422
Max Act: 5.0172. Min Act: -0.1700
Data Index: 2067712 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.9234. Min Act: -0.1700
Data Index: 5710002 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.9547. Min Act: -0.1700
Data Index: 573491 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.9234. Min Act: -0.1700
Data Index: 3875260 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.9234. Min Act: -0.1700
Data Index: 8293493 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.9234. Min Act: -0.1700
Data Index: 3674753 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.8922. Min Act: -0.1700
Data Index: 3396690 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.8922. Min Act: -0.1700
Data Index: 6605372 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.8922. Min Act: -0.1700
Data Index: 8805338 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.8922. Min Act: -0.1700
Data Index: 1516454 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1422. Min Range: -5.1422
Max Act: 4.8922. Min Act: -0.1700
Data Index: 7000949 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19