Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.5350. Min Act: -0.1700
Data Index: 5976150 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.5037. Min Act: -0.1700
Data Index: 5266806 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.4100. Min Act: -0.1700
Data Index: 5245958 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3787. Min Act: -0.1700
Data Index: 1705429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3787. Min Act: -0.1700
Data Index: 3125059 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3787. Min Act: -0.1700
Data Index: 6657092 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3475. Min Act: -0.1700
Data Index: 5597220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3475. Min Act: -0.1700
Data Index: 1053506 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3475. Min Act: -0.1699
Data Index: 8776816 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3475. Min Act: -0.1660
Data Index: 7203320 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3162. Min Act: -0.1700
Data Index: 3597830 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3162. Min Act: -0.1699
Data Index: 7428421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3162. Min Act: -0.1685
Data Index: 5201617 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3162. Min Act: -0.1700
Data Index: 6168649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3162. Min Act: -0.1700
Data Index: 7442783 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3162. Min Act: -0.1683
Data Index: 332401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.3162. Min Act: -0.1700
Data Index: 5783931 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.2537. Min Act: -0.1700
Data Index: 6303048 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.2850. Min Act: -0.1700
Data Index: 3604981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5350. Min Range: -4.5350
Max Act: 4.2850. Min Act: -0.1610
Data Index: 4325994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19