Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5678 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.5587. Min Act: -0.1700
Data Index: 1281536 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.5275. Min Act: -0.1700
Data Index: 3017933 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.4337. Min Act: -0.1700
Data Index: 7471432 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.4337. Min Act: -0.1700
Data Index: 2146648 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.4337. Min Act: -0.1700
Data Index: 4078555 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.4650. Min Act: -0.1700
Data Index: 5546582 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.4337. Min Act: -0.1700
Data Index: 2548018 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.4025. Min Act: -0.1700
Data Index: 2372083 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3712. Min Act: -0.1700
Data Index: 855414 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3712. Min Act: -0.1700
Data Index: 632685 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3712. Min Act: -0.1700
Data Index: 7159732 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3712. Min Act: -0.1700
Data Index: 7072835 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3400. Min Act: -0.1700
Data Index: 6762585 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3712. Min Act: -0.1700
Data Index: 1157074 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3400. Min Act: -0.1700
Data Index: 5836019 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3087. Min Act: -0.1700
Data Index: 3641898 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3400. Min Act: -0.1700
Data Index: 7095989 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3087. Min Act: -0.1700
Data Index: 5078034 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3400. Min Act: -0.1700
Data Index: 5028212 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5587. Min Range: -5.5587
Max Act: 5.3400. Min Act: -0.1700
Data Index: 1082989 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19