Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3115 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0649. Min Range: -5.0649
Max Act: 5.0649. Min Act: -0.1700
Data Index: 2943317 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0649. Min Range: -5.0649
Max Act: 5.0336. Min Act: -0.1700
Data Index: 2579196 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0649. Min Range: -5.0649
Max Act: 5.0024. Min Act: -0.1700
Data Index: 4532215 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0649. Min Range: -5.0649
Max Act: 5.0024. Min Act: -0.1700
Data Index: 8697222 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0649. Min Range: -5.0649
Max Act: 5.0024. Min Act: -0.1700
Data Index: 6213454 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.9711. Min Act: -0.1700
Data Index: 3949486 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.9711. Min Act: -0.1700
Data Index: 6051588 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.9399. Min Act: -0.1700
Data Index: 2928965 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.9711. Min Act: -0.1700
Data Index: 3063604 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.9086. Min Act: -0.1700
Data Index: 3414728 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.9086. Min Act: -0.1700
Data Index: 2680766 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.8774. Min Act: -0.1700
Data Index: 5659645 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.8461. Min Act: -0.1700
Data Index: 8146685 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.8149. Min Act: -0.1700
Data Index: 2865527 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.8149. Min Act: -0.1700
Data Index: 6530360 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.8149. Min Act: -0.1700
Data Index: 3526741 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.8149. Min Act: -0.1700
Data Index: 3328787 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.8149. Min Act: -0.1700
Data Index: 8480584 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.7836. Min Act: -0.1700
Data Index: 2220898 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0649. Min Range: -5.0649
Max Act: 4.7524. Min Act: -0.1700
Data Index: 6539196 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19