Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2205 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.2799. Min Act: -0.1700
Data Index: 8698514 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.2174. Min Act: -0.1700
Data Index: 2192697 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.1549. Min Act: -0.1700
Data Index: 2101241 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.1549. Min Act: -0.1700
Data Index: 7056377 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.1549. Min Act: -0.1700
Data Index: 1797677 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.1549. Min Act: -0.1700
Data Index: 122092 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.1549. Min Act: -0.1700
Data Index: 4214079 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.1237. Min Act: -0.1700
Data Index: 8795339 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.1549. Min Act: -0.1700
Data Index: 5783103 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.1549. Min Act: -0.1700
Data Index: 743929 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.1237. Min Act: -0.1700
Data Index: 1654131 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.0924. Min Act: -0.1700
Data Index: 8127607 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.0612. Min Act: -0.1699
Data Index: 4783456 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.0924. Min Act: -0.1700
Data Index: 3233288 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.0924. Min Act: -0.1700
Data Index: 4942043 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.0924. Min Act: -0.1700
Data Index: 4787317 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.0612. Min Act: -0.1700
Data Index: 7816410 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.0612. Min Act: -0.1700
Data Index: 7885387 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.0612. Min Act: -0.1700
Data Index: 8107244 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2799. Min Range: -5.2799
Max Act: 5.0612. Min Act: -0.1700
Data Index: 2011696 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19