Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5009 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5045. Min Range: -6.5045
Max Act: 6.5045. Min Act: -0.1700
Data Index: 3778664 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5045. Min Range: -6.5045
Max Act: 6.1295. Min Act: -0.1700
Data Index: 4344984 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5045. Min Range: -6.5045
Max Act: 6.0358. Min Act: -0.1700
Data Index: 555662 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5045. Min Range: -6.5045
Max Act: 6.0045. Min Act: -0.1700
Data Index: 7969924 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.9420. Min Act: -0.1700
Data Index: 7265759 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.9108. Min Act: -0.1700
Data Index: 176469 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.9108. Min Act: -0.1700
Data Index: 7632617 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.8795. Min Act: -0.1700
Data Index: 5090938 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.8483. Min Act: -0.1700
Data Index: 5701077 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.8483. Min Act: -0.1700
Data Index: 3580308 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.8483. Min Act: -0.1700
Data Index: 6467239 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.8483. Min Act: -0.1700
Data Index: 759950 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.8483. Min Act: -0.1700
Data Index: 7059376 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.8170. Min Act: -0.1700
Data Index: 5895482 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.7858. Min Act: -0.1700
Data Index: 5212666 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.7545. Min Act: -0.1700
Data Index: 7579136 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.8170. Min Act: -0.1700
Data Index: 2185984 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.7545. Min Act: -0.1700
Data Index: 5204693 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.7233. Min Act: -0.1700
Data Index: 4816675 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5045. Min Range: -6.5045
Max Act: 5.7545. Min Act: -0.1700
Data Index: 7111586 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19