Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.2108. Min Act: -0.1700
Data Index: 987412 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.1483. Min Act: -0.1700
Data Index: 6941116 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.1795. Min Act: -0.1700
Data Index: 7709946 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.1483. Min Act: -0.1700
Data Index: 5892836 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.1483. Min Act: -0.1700
Data Index: 2092008 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.1483. Min Act: -0.1700
Data Index: 8532075 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.1170. Min Act: -0.1700
Data Index: 6447974 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.1170. Min Act: -0.1700
Data Index: 4996160 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.1170. Min Act: -0.1700
Data Index: 8759645 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0858. Min Act: -0.1700
Data Index: 4927228 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0545. Min Act: -0.1700
Data Index: 84786 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0858. Min Act: -0.1700
Data Index: 1273923 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0858. Min Act: -0.1697
Data Index: 1089372 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0858. Min Act: -0.1700
Data Index: 4774315 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0858. Min Act: -0.1700
Data Index: 7110996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0545. Min Act: -0.1700
Data Index: 3381235 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0545. Min Act: -0.1700
Data Index: 1115601 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0545. Min Act: -0.1700
Data Index: 5319606 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0545. Min Act: -0.1700
Data Index: 5517479 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0545. Min Act: -0.1699
Data Index: 3754638 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19