Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2161 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.5700. Min Act: -0.1700
Data Index: 5679062 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.4450. Min Act: -0.1700
Data Index: 6357727 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.4762. Min Act: -0.1700
Data Index: 2453566 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3825. Min Act: -0.1700
Data Index: 6853838 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3512. Min Act: -0.1700
Data Index: 8366365 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2575. Min Act: -0.1700
Data Index: 5119757 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2887. Min Act: -0.1700
Data Index: 3279165 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2887. Min Act: -0.1700
Data Index: 4315178 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2887. Min Act: -0.1700
Data Index: 3016799 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2887. Min Act: -0.1700
Data Index: 1090617 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2887. Min Act: -0.1700
Data Index: 7051547 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2575. Min Act: -0.1700
Data Index: 8430402 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2575. Min Act: -0.1700
Data Index: 6523289 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2262. Min Act: -0.1700
Data Index: 4315174 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2262. Min Act: -0.1700
Data Index: 1668947 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2262. Min Act: -0.1700
Data Index: 3797963 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.1950. Min Act: -0.1700
Data Index: 5134047 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.1950. Min Act: -0.1700
Data Index: 3576990 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.1637. Min Act: -0.1700
Data Index: 5569927 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.1637. Min Act: -0.1700
Data Index: 4735276 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19