Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1438 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2524. Min Range: -7.2524
Max Act: 7.2524. Min Act: -0.1700
Data Index: 517806 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2524. Min Range: -7.2524
Max Act: 7.1899. Min Act: -0.1700
Data Index: 4892517 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2524. Min Range: -7.2524
Max Act: 7.0962. Min Act: -0.1700
Data Index: 6459609 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2524. Min Range: -7.2524
Max Act: 7.0962. Min Act: -0.1700
Data Index: 36748 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2524. Min Range: -7.2524
Max Act: 7.0337. Min Act: -0.1700
Data Index: 283206 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2524. Min Range: -7.2524
Max Act: 7.0024. Min Act: -0.1700
Data Index: 5752878 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2524. Min Range: -7.2524
Max Act: 7.0024. Min Act: -0.1700
Data Index: 6237530 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.9712. Min Act: -0.1700
Data Index: 8180038 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.9712. Min Act: -0.1700
Data Index: 6226662 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.9712. Min Act: -0.1700
Data Index: 2630623 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.9712. Min Act: -0.1700
Data Index: 6237529 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.9399. Min Act: -0.1700
Data Index: 3742711 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.9399. Min Act: -0.1700
Data Index: 7305346 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.9712. Min Act: -0.1700
Data Index: 3583454 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.9087. Min Act: -0.1700
Data Index: 6828295 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.9087. Min Act: -0.1700
Data Index: 5040317 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.9087. Min Act: -0.1700
Data Index: 2950201 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.9087. Min Act: -0.1700
Data Index: 4773760 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.8774. Min Act: -0.1700
Data Index: 4206182 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2524. Min Range: -7.2524
Max Act: 6.8774. Min Act: -0.1700
Data Index: 5040316 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19