Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.5867. Min Act: -0.1700
Data Index: 8139948 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.5867. Min Act: -0.1700
Data Index: 7970464 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.5242. Min Act: -0.1700
Data Index: 3194434 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.4617. Min Act: -0.1700
Data Index: 5488910 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.4305. Min Act: -0.1700
Data Index: 7163806 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.3680. Min Act: -0.1700
Data Index: 6384092 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.3680. Min Act: -0.1700
Data Index: 1919021 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.3680. Min Act: -0.1700
Data Index: 2793740 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.3367. Min Act: -0.1700
Data Index: 3071703 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.3367. Min Act: -0.1700
Data Index: 5705063 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.3055. Min Act: -0.1700
Data Index: 2206696 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.2430. Min Act: -0.1700
Data Index: 3782795 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.2742. Min Act: -0.1700
Data Index: 4805148 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.2117. Min Act: -0.1700
Data Index: 7996725 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.2430. Min Act: -0.1700
Data Index: 1429609 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.2117. Min Act: -0.1700
Data Index: 5976062 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.2117. Min Act: -0.1700
Data Index: 6150270 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.2430. Min Act: -0.1700
Data Index: 6702813 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.2117. Min Act: -0.1700
Data Index: 815287 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5867. Min Range: -7.5867
Max Act: 7.1805. Min Act: -0.1700
Data Index: 5486978 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19