Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1347 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.5547. Min Act: -0.1700
Data Index: 6684578 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.2734. Min Act: -0.1700
Data Index: 5853025 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.2734. Min Act: -0.1700
Data Index: 97967 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.2734. Min Act: -0.1700
Data Index: 97970 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.3047. Min Act: -0.1700
Data Index: 4827086 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.2422. Min Act: -0.1700
Data Index: 97968 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.2422. Min Act: -0.1700
Data Index: 1561565 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.2422. Min Act: -0.1700
Data Index: 7018093 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.1797. Min Act: -0.1700
Data Index: 6138252 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.2109. Min Act: -0.1700
Data Index: 7018089 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.2109. Min Act: -0.1700
Data Index: 490885 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.2109. Min Act: -0.1700
Data Index: 6763774 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.1797. Min Act: -0.1700
Data Index: 855644 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.1484. Min Act: -0.1700
Data Index: 1597447 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.1484. Min Act: -0.1700
Data Index: 8665265 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.1172. Min Act: -0.1700
Data Index: 8004526 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.1484. Min Act: -0.1700
Data Index: 4211156 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.1172. Min Act: -0.1700
Data Index: 5707033 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.1172. Min Act: -0.1700
Data Index: 855643 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5547. Min Range: -4.5547
Max Act: 4.0859. Min Act: -0.1700
Data Index: 7591088 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19