Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2366 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.4622. Min Act: -0.1700
Data Index: 2959369 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.3644. Min Act: -0.1700
Data Index: 2962857 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.2988. Min Act: -0.1700
Data Index: 6227732 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.2658. Min Act: -0.1700
Data Index: 4792772 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.2493. Min Act: -0.1700
Data Index: 5293545 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.2493. Min Act: -0.1700
Data Index: 5558137 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.2493. Min Act: -0.1700
Data Index: 1060179 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.2493. Min Act: -0.1700
Data Index: 3183048 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.2328. Min Act: -0.1700
Data Index: 78126 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.2162. Min Act: -0.1700
Data Index: 5134143 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.1996. Min Act: -0.1700
Data Index: 6778667 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.1996. Min Act: -0.1700
Data Index: 8682981 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.1996. Min Act: -0.1700
Data Index: 3366428 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.1664. Min Act: -0.1700
Data Index: 6461323 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.1830. Min Act: -0.1700
Data Index: 2647998 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.1830. Min Act: -0.1700
Data Index: 4030319 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.1497. Min Act: -0.1700
Data Index: 4927905 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.1664. Min Act: -0.1700
Data Index: 4030320 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.1664. Min Act: -0.1700
Data Index: 8449450 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4622. Min Range: -2.4622
Max Act: 2.1664. Min Act: -0.1700
Data Index: 3096280 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19