Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0200. Min Range: -9.0200
Max Act: 9.0200. Min Act: -0.1700
Data Index: 3619195 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.9575. Min Act: -0.1700
Data Index: 3312303 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.8950. Min Act: -0.1700
Data Index: 8141399 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.9575. Min Act: -0.1700
Data Index: 1922017 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.8950. Min Act: -0.1700
Data Index: 3892923 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.8950. Min Act: -0.1700
Data Index: 5106108 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.8950. Min Act: -0.1700
Data Index: 1845263 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.8950. Min Act: -0.1700
Data Index: 3619196 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.8325. Min Act: -0.1700
Data Index: 328354 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.8325. Min Act: -0.1700
Data Index: 6004497 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.7700. Min Act: -0.1700
Data Index: 7343168 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.7700. Min Act: -0.1700
Data Index: 4342005 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.7700. Min Act: -0.1700
Data Index: 1400809 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.8325. Min Act: -0.1700
Data Index: 4138800 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.8325. Min Act: -0.1700
Data Index: 1542796 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.7075. Min Act: -0.1700
Data Index: 852521 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.7075. Min Act: -0.1700
Data Index: 2567744 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.7075. Min Act: -0.1700
Data Index: 7746318 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.7700. Min Act: -0.1700
Data Index: 4956459 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0200. Min Range: -9.0200
Max Act: 8.7075. Min Act: -0.1700
Data Index: 8728580 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19