Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1968 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.6646. Min Act: -0.1700
Data Index: 8303490 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.4771. Min Act: -0.1700
Data Index: 2507582 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.4146. Min Act: -0.1700
Data Index: 472838 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.3521. Min Act: -0.1700
Data Index: 6089058 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.3521. Min Act: -0.1700
Data Index: 2879324 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.3208. Min Act: -0.1700
Data Index: 4826974 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.2896. Min Act: -0.1700
Data Index: 1302514 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.2583. Min Act: -0.1700
Data Index: 6521774 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.1646. Min Act: -0.1700
Data Index: 3795112 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.1333. Min Act: -0.1700
Data Index: 3285669 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.1021. Min Act: -0.1700
Data Index: 1255094 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.1333. Min Act: -0.1700
Data Index: 290077 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.1333. Min Act: -0.1700
Data Index: 192444 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.1646. Min Act: -0.1700
Data Index: 6359739 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.0708. Min Act: -0.1700
Data Index: 8599501 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.1021. Min Act: -0.1700
Data Index: 3467758 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.1021. Min Act: -0.1700
Data Index: 7952467 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.1021. Min Act: -0.1700
Data Index: 2648378 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.1021. Min Act: -0.1700
Data Index: 3981252 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6646. Min Range: -6.6646
Max Act: 6.1021. Min Act: -0.1700
Data Index: 1742724 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19