Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0707. Min Range: -9.0707
Max Act: 9.0707. Min Act: -0.1700
Data Index: 2899398 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.7582. Min Act: -0.1700
Data Index: 86516 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.6332. Min Act: -0.1700
Data Index: 3071911 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.5707. Min Act: -0.1700
Data Index: 6302277 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.5082. Min Act: -0.1700
Data Index: 7879959 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.5082. Min Act: -0.1700
Data Index: 3958990 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.3207. Min Act: -0.1700
Data Index: 8540518 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.2582. Min Act: -0.1700
Data Index: 1669417 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.1957. Min Act: -0.1700
Data Index: 5549455 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.2582. Min Act: -0.1700
Data Index: 5234896 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.2582. Min Act: -0.1700
Data Index: 4108809 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.2582. Min Act: -0.1700
Data Index: 1493627 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.1957. Min Act: -0.1700
Data Index: 6297925 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.1957. Min Act: -0.1700
Data Index: 6351945 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.1957. Min Act: -0.1700
Data Index: 8604164 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.1332. Min Act: -0.1700
Data Index: 7051605 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.1957. Min Act: -0.1700
Data Index: 3476764 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.1332. Min Act: -0.1700
Data Index: 1503731 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.1332. Min Act: -0.1700
Data Index: 6303462 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0707. Min Range: -9.0707
Max Act: 8.1019. Min Act: -0.1700
Data Index: 316188 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19