Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2375 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5873. Min Act: -0.1700
Data Index: 2965771 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5873. Min Act: -0.1700
Data Index: 7480198 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5873. Min Act: -0.1700
Data Index: 8061002 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5712. Min Act: -0.1700
Data Index: 1446563 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5551. Min Act: -0.1700
Data Index: 6463065 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5551. Min Act: -0.1700
Data Index: 197034 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5389. Min Act: -0.1700
Data Index: 3358803 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5551. Min Act: -0.1700
Data Index: 2154045 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5551. Min Act: -0.1700
Data Index: 6391066 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5227. Min Act: -0.1700
Data Index: 4673593 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5227. Min Act: -0.1700
Data Index: 8712830 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5227. Min Act: -0.1700
Data Index: 6053119 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5227. Min Act: -0.1700
Data Index: 1559692 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5066. Min Act: -0.1700
Data Index: 4293075 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5066. Min Act: -0.1700
Data Index: 7649196 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5066. Min Act: -0.1700
Data Index: 561649 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.5066. Min Act: -0.1700
Data Index: 4047278 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.4904. Min Act: -0.1700
Data Index: 7880495 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.4904. Min Act: -0.1700
Data Index: 6253075 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5873. Min Range: -2.5873
Max Act: 2.4904. Min Act: -0.1700
Data Index: 3214404 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19