Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.7858. Min Act: -0.1700
Data Index: 3015937 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.6608. Min Act: -0.1700
Data Index: 5861203 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.5983. Min Act: -0.1700
Data Index: 5557229 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.5046. Min Act: -0.1700
Data Index: 331550 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.5046. Min Act: -0.1700
Data Index: 4585018 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.5046. Min Act: -0.1700
Data Index: 2670686 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.4733. Min Act: -0.1700
Data Index: 7179752 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.4421. Min Act: -0.1700
Data Index: 3051640 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.4421. Min Act: -0.1700
Data Index: 5922728 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.4421. Min Act: -0.1700
Data Index: 3589971 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.4108. Min Act: -0.1700
Data Index: 4021657 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.4108. Min Act: -0.1700
Data Index: 5125711 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.4108. Min Act: -0.1700
Data Index: 1493997 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.4108. Min Act: -0.1700
Data Index: 3443208 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.4108. Min Act: -0.1700
Data Index: 1489487 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.3796. Min Act: -0.1700
Data Index: 2471431 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.3796. Min Act: -0.1700
Data Index: 5932237 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.3796. Min Act: -0.1700
Data Index: 6550583 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.3796. Min Act: -0.1700
Data Index: 1169072 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7858. Min Range: -4.7858
Max Act: 4.3796. Min Act: -0.1700
Data Index: 1437326 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19