Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5345 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.8321. Min Act: -0.1700
Data Index: 8318446 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.6759. Min Act: -0.1700
Data Index: 7683650 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.6134. Min Act: -0.1700
Data Index: 8123449 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.5821. Min Act: -0.1700
Data Index: 3255171 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.5509. Min Act: -0.1700
Data Index: 4013171 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.5196. Min Act: -0.1700
Data Index: 6354905 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.4884. Min Act: -0.1700
Data Index: 4243924 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.4571. Min Act: -0.1700
Data Index: 5831248 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.4259. Min Act: -0.1700
Data Index: 7289163 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.4259. Min Act: -0.1700
Data Index: 7489858 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.3634. Min Act: -0.1700
Data Index: 1696346 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.3634. Min Act: -0.1700
Data Index: 2685319 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.3321. Min Act: -0.1700
Data Index: 7112341 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.3321. Min Act: -0.1700
Data Index: 1806097 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.3321. Min Act: -0.1700
Data Index: 3155373 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.2696. Min Act: -0.1700
Data Index: 429936 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.3009. Min Act: -0.1700
Data Index: 7445036 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.2696. Min Act: -0.1700
Data Index: 6582271 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.3009. Min Act: -0.1700
Data Index: 5375422 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8321. Min Range: -7.8321
Max Act: 7.2384. Min Act: -0.1700
Data Index: 7495844 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19