Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3160 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0345. Min Range: -6.0345
Max Act: 6.0345. Min Act: -0.1700
Data Index: 3983424 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.8158. Min Act: -0.1700
Data Index: 3644958 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.8158. Min Act: -0.1700
Data Index: 7714629 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7845. Min Act: -0.1700
Data Index: 1018510 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7845. Min Act: -0.1697
Data Index: 7239796 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7845. Min Act: -0.1700
Data Index: 7713898 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7845. Min Act: -0.1699
Data Index: 3025535 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7533. Min Act: -0.1700
Data Index: 2048102 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7533. Min Act: -0.1700
Data Index: 3437598 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7220. Min Act: -0.1700
Data Index: 3400831 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7220. Min Act: -0.1700
Data Index: 5780514 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7533. Min Act: -0.1700
Data Index: 5758728 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7533. Min Act: -0.1700
Data Index: 7714628 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7533. Min Act: -0.1700
Data Index: 4567475 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7220. Min Act: -0.1700
Data Index: 5652008 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7220. Min Act: -0.1700
Data Index: 412555 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7220. Min Act: -0.1700
Data Index: 8224456 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7220. Min Act: -0.1700
Data Index: 4938013 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.7220. Min Act: -0.1700
Data Index: 6104837 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0345. Min Range: -6.0345
Max Act: 5.6908. Min Act: -0.1700
Data Index: 192154 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19