Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0669. Min Range: -6.0669
Max Act: 6.0669. Min Act: -0.1700
Data Index: 8700187 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.9419. Min Act: -0.1700
Data Index: 4719395 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.9732. Min Act: -0.1700
Data Index: 3483305 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.8169. Min Act: -0.1700
Data Index: 6846188 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.8169. Min Act: -0.1700
Data Index: 142866 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7857. Min Act: -0.1700
Data Index: 7072634 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7857. Min Act: -0.1700
Data Index: 688638 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7857. Min Act: -0.1700
Data Index: 4507851 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7857. Min Act: -0.1700
Data Index: 5595339 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7857. Min Act: -0.1700
Data Index: 3805515 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7544. Min Act: -0.1700
Data Index: 570514 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7544. Min Act: -0.1700
Data Index: 813235 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7544. Min Act: -0.1700
Data Index: 1734605 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7544. Min Act: -0.1700
Data Index: 3872817 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7857. Min Act: -0.1700
Data Index: 3741635 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7857. Min Act: -0.1700
Data Index: 7542205 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7232. Min Act: -0.1700
Data Index: 6369203 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7232. Min Act: -0.1700
Data Index: 7084646 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7232. Min Act: -0.1700
Data Index: 3440415 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0669. Min Range: -6.0669
Max Act: 5.7232. Min Act: -0.1700
Data Index: 1353700 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19