Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.3167. Min Act: -0.1700
Data Index: 5510463 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.1917. Min Act: -0.1700
Data Index: 1159747 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.9729. Min Act: -0.1700
Data Index: 7518593 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.0042. Min Act: -0.1700
Data Index: 7665666 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.9416. Min Act: -0.1700
Data Index: 1479375 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.9416. Min Act: -0.1700
Data Index: 907554 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.8791. Min Act: -0.1700
Data Index: 3168989 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.8791. Min Act: -0.1700
Data Index: 6241744 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.8635. Min Act: -0.1700
Data Index: 6786910 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.8635. Min Act: -0.1700
Data Index: 2224136 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.8478. Min Act: -0.1700
Data Index: 146762 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.8322. Min Act: -0.1700
Data Index: 1245769 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.8009. Min Act: -0.1700
Data Index: 6920038 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.8009. Min Act: -0.1700
Data Index: 3955415 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.8166. Min Act: -0.1700
Data Index: 2579610 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.8166. Min Act: -0.1700
Data Index: 8262361 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.7853. Min Act: -0.1700
Data Index: 5210689 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.7853. Min Act: -0.1700
Data Index: 3919267 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.7853. Min Act: -0.1700
Data Index: 2744889 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3167. Min Range: -4.3167
Max Act: 3.8009. Min Act: -0.1700
Data Index: 6628296 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19