Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.2639. Min Act: -0.1700
Data Index: 1896607 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.2326. Min Act: -0.1700
Data Index: 2250406 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.2014. Min Act: -0.1700
Data Index: 3114520 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.2326. Min Act: -0.1700
Data Index: 6891227 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.2014. Min Act: -0.1700
Data Index: 5680397 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.2014. Min Act: -0.1700
Data Index: 928694 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.2014. Min Act: -0.1700
Data Index: 4631703 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.1701. Min Act: -0.1700
Data Index: 3650361 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.1701. Min Act: -0.1700
Data Index: 179601 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.1701. Min Act: -0.1700
Data Index: 3063588 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.1701. Min Act: -0.1700
Data Index: 7937453 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.1701. Min Act: -0.1700
Data Index: 2666837 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.1389. Min Act: -0.1700
Data Index: 1504556 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.1076. Min Act: -0.1700
Data Index: 7005444 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.1389. Min Act: -0.1700
Data Index: 2620870 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.1076. Min Act: -0.1700
Data Index: 3891773 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.1389. Min Act: -0.1700
Data Index: 2889238 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.0764. Min Act: -0.1700
Data Index: 3795924 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.0451. Min Act: -0.1700
Data Index: 6704228 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2639. Min Range: -4.2639
Max Act: 4.0764. Min Act: -0.1700
Data Index: 6953275 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19