Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 84 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.8091. Min Act: -0.1700
Data Index: 3745427 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.8091. Min Act: -0.1700
Data Index: 7281152 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7779. Min Act: -0.1700
Data Index: 1111610 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7779. Min Act: -0.1700
Data Index: 3621489 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7466. Min Act: -0.1699
Data Index: 5689076 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7466. Min Act: -0.1700
Data Index: 5884428 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7154. Min Act: -0.1700
Data Index: 1246399 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7154. Min Act: -0.1700
Data Index: 5351363 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7466. Min Act: -0.1700
Data Index: 3761228 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7466. Min Act: -0.1690
Data Index: 2097879 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7154. Min Act: -0.1692
Data Index: 5230909 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7154. Min Act: -0.1700
Data Index: 1779733 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7154. Min Act: -0.1697
Data Index: 5078710 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7154. Min Act: -0.1700
Data Index: 4647080 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7154. Min Act: -0.1700
Data Index: 2084168 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7154. Min Act: -0.1698
Data Index: 7971590 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7154. Min Act: -0.1700
Data Index: 4262996 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7154. Min Act: -0.1698
Data Index: 2946788 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7154. Min Act: -0.1700
Data Index: 342050 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.6841. Min Act: -0.1700
Data Index: 2361885 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19