Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2028 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1900. Min Range: -5.1900
Max Act: 5.1900. Min Act: -0.1700
Data Index: 8128004 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1900. Min Range: -5.1900
Max Act: 5.1587. Min Act: -0.1700
Data Index: 4525062 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1900. Min Range: -5.1900
Max Act: 5.1587. Min Act: -0.1700
Data Index: 1267665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1900. Min Range: -5.1900
Max Act: 5.1275. Min Act: -0.1700
Data Index: 833213 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1900. Min Range: -5.1900
Max Act: 5.1275. Min Act: -0.1700
Data Index: 3037928 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1900. Min Range: -5.1900
Max Act: 5.0962. Min Act: -0.1700
Data Index: 1274676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1900. Min Range: -5.1900
Max Act: 5.0962. Min Act: -0.1700
Data Index: 1649987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1900. Min Range: -5.1900
Max Act: 5.0337. Min Act: -0.1700
Data Index: 2055329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1900. Min Range: -5.1900
Max Act: 5.0337. Min Act: -0.1699
Data Index: 1420178 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1900. Min Range: -5.1900
Max Act: 5.0025. Min Act: -0.1700
Data Index: 6434045 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1900. Min Range: -5.1900
Max Act: 5.0025. Min Act: -0.1700
Data Index: 8033467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1900. Min Range: -5.1900
Max Act: 4.9712. Min Act: -0.1700
Data Index: 4920217 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1900. Min Range: -5.1900
Max Act: 4.9712. Min Act: -0.1700
Data Index: 1045923 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1900. Min Range: -5.1900
Max Act: 4.9712. Min Act: -0.1700
Data Index: 6598908 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1900. Min Range: -5.1900
Max Act: 4.9400. Min Act: -0.1700
Data Index: 15725 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1900. Min Range: -5.1900
Max Act: 4.9400. Min Act: -0.1700
Data Index: 8499701 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1900. Min Range: -5.1900
Max Act: 4.9400. Min Act: -0.1700
Data Index: 3294106 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1900. Min Range: -5.1900
Max Act: 4.9400. Min Act: -0.1700
Data Index: 3528695 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1900. Min Range: -5.1900
Max Act: 4.9400. Min Act: -0.1700
Data Index: 4190105 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1900. Min Range: -5.1900
Max Act: 4.9712. Min Act: -0.1700
Data Index: 6706684 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19