Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0496. Min Range: -5.0496
Max Act: 5.0496. Min Act: -0.1700
Data Index: 624565 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0496. Min Range: -5.0496
Max Act: 5.0184. Min Act: -0.1700
Data Index: 1401783 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0496. Min Range: -5.0496
Max Act: 5.0496. Min Act: -0.1700
Data Index: 7024283 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.9559. Min Act: -0.1700
Data Index: 1275446 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.9559. Min Act: -0.1700
Data Index: 4801354 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.9559. Min Act: -0.1700
Data Index: 3326197 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.8934. Min Act: -0.1700
Data Index: 8020365 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.9246. Min Act: -0.1700
Data Index: 5856406 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.9246. Min Act: -0.1700
Data Index: 1738673 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.9246. Min Act: -0.1700
Data Index: 7970359 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.8934. Min Act: -0.1700
Data Index: 4355652 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.8934. Min Act: -0.1700
Data Index: 6901992 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.8621. Min Act: -0.1700
Data Index: 149705 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.8309. Min Act: -0.1700
Data Index: 4229629 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.8621. Min Act: -0.1700
Data Index: 2592122 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.8309. Min Act: -0.1700
Data Index: 4134058 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.8621. Min Act: -0.1700
Data Index: 572813 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.8309. Min Act: -0.1700
Data Index: 4472397 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.9246. Min Act: -0.1700
Data Index: 2369501 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0496. Min Range: -5.0496
Max Act: 4.8934. Min Act: -0.1700
Data Index: 4344076 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19