Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.3690. Min Act: -0.1700
Data Index: 1358413 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.3378. Min Act: -0.1700
Data Index: 3506731 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.1815. Min Act: -0.1700
Data Index: 3746217 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.1502. Min Act: -0.1700
Data Index: 6573134 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.1502. Min Act: -0.1700
Data Index: 5745805 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.1190. Min Act: -0.1700
Data Index: 2734271 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.0877. Min Act: -0.1700
Data Index: 846078 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.0877. Min Act: -0.1700
Data Index: 2382036 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.0565. Min Act: -0.1700
Data Index: 2393339 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.0252. Min Act: -0.1700
Data Index: 7292681 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3690. Min Range: -4.3690
Max Act: 3.9940. Min Act: -0.1700
Data Index: 4073168 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.0252. Min Act: -0.1700
Data Index: 3387186 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.0252. Min Act: -0.1700
Data Index: 3468869 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.0252. Min Act: -0.1700
Data Index: 7779164 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3690. Min Range: -4.3690
Max Act: 4.0252. Min Act: -0.1700
Data Index: 7274497 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3690. Min Range: -4.3690
Max Act: 3.9940. Min Act: -0.1700
Data Index: 7362492 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3690. Min Range: -4.3690
Max Act: 3.9940. Min Act: -0.1700
Data Index: 3007942 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3690. Min Range: -4.3690
Max Act: 3.9627. Min Act: -0.1700
Data Index: 5365406 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3690. Min Range: -4.3690
Max Act: 3.9627. Min Act: -0.1700
Data Index: 2636966 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3690. Min Range: -4.3690
Max Act: 3.9627. Min Act: -0.1700
Data Index: 1225052 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19