Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2873 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3715. Min Range: -5.3715
Max Act: 5.3715. Min Act: -0.1700
Data Index: 8260206 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3715. Min Range: -5.3715
Max Act: 5.3090. Min Act: -0.1700
Data Index: 5005029 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3715. Min Range: -5.3715
Max Act: 5.2153. Min Act: -0.1700
Data Index: 1360321 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3715. Min Range: -5.3715
Max Act: 5.1528. Min Act: -0.1700
Data Index: 4497860 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3715. Min Range: -5.3715
Max Act: 5.1215. Min Act: -0.1700
Data Index: 3839236 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3715. Min Range: -5.3715
Max Act: 5.0903. Min Act: -0.1700
Data Index: 3762007 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3715. Min Range: -5.3715
Max Act: 5.0278. Min Act: -0.1700
Data Index: 114627 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.9965. Min Act: -0.1700
Data Index: 3154124 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.9340. Min Act: -0.1700
Data Index: 2694721 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.9340. Min Act: -0.1700
Data Index: 3306409 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.9028. Min Act: -0.1700
Data Index: 1259927 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.9028. Min Act: -0.1700
Data Index: 5330682 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.8715. Min Act: -0.1700
Data Index: 65384 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.8715. Min Act: -0.1700
Data Index: 6579127 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.8403. Min Act: -0.1700
Data Index: 2957187 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.8403. Min Act: -0.1700
Data Index: 5198176 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.8403. Min Act: -0.1700
Data Index: 6367701 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.8403. Min Act: -0.1700
Data Index: 8149971 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.8403. Min Act: -0.1700
Data Index: 3313642 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3715. Min Range: -5.3715
Max Act: 4.8090. Min Act: -0.1700
Data Index: 5195281 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19