Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1549 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.2413. Min Act: -0.1700
Data Index: 590565 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.2101. Min Act: -0.1700
Data Index: 7534140 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.1476. Min Act: -0.1700
Data Index: 3941115 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.1163. Min Act: -0.1700
Data Index: 5517879 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0538. Min Act: -0.1700
Data Index: 7484855 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0851. Min Act: -0.1700
Data Index: 1114844 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0851. Min Act: -0.1700
Data Index: 8352008 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.1163. Min Act: -0.1700
Data Index: 3965210 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0226. Min Act: -0.1700
Data Index: 5858985 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0226. Min Act: -0.1700
Data Index: 1819958 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2413. Min Range: -5.2413
Max Act: 4.9913. Min Act: -0.1700
Data Index: 8662895 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0538. Min Act: -0.1700
Data Index: 7552634 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0538. Min Act: -0.1700
Data Index: 3628808 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0538. Min Act: -0.1700
Data Index: 7546931 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0538. Min Act: -0.1700
Data Index: 6309120 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0851. Min Act: -0.1700
Data Index: 6717470 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2413. Min Range: -5.2413
Max Act: 4.9913. Min Act: -0.1700
Data Index: 5576283 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2413. Min Range: -5.2413
Max Act: 4.9913. Min Act: -0.1700
Data Index: 350478 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2413. Min Range: -5.2413
Max Act: 4.9913. Min Act: -0.1700
Data Index: 5576286 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2413. Min Range: -5.2413
Max Act: 4.9913. Min Act: -0.1700
Data Index: 1675704 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19