Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6679. Min Range: -8.6679
Max Act: 8.6679. Min Act: -0.1700
Data Index: 466880 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6679. Min Range: -8.6679
Max Act: 8.2929. Min Act: -0.1700
Data Index: 849415 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6679. Min Range: -8.6679
Max Act: 8.1679. Min Act: -0.1700
Data Index: 6683213 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6679. Min Range: -8.6679
Max Act: 8.1054. Min Act: -0.1700
Data Index: 8082964 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6679. Min Range: -8.6679
Max Act: 8.1054. Min Act: -0.1700
Data Index: 5903767 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6679. Min Range: -8.6679
Max Act: 8.0429. Min Act: -0.1700
Data Index: 1395458 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.9804. Min Act: -0.1700
Data Index: 1184381 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.8867. Min Act: -0.1700
Data Index: 2991325 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.8242. Min Act: -0.1700
Data Index: 2961828 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.7929. Min Act: -0.1700
Data Index: 3116176 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.6992. Min Act: -0.1700
Data Index: 3827963 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.7304. Min Act: -0.1700
Data Index: 6226040 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.7304. Min Act: -0.1700
Data Index: 7354744 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.6992. Min Act: -0.1700
Data Index: 6928427 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.6992. Min Act: -0.1700
Data Index: 3742923 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.6679. Min Act: -0.1700
Data Index: 3787687 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.7304. Min Act: -0.1700
Data Index: 3879341 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.6992. Min Act: -0.1700
Data Index: 5599833 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.6679. Min Act: -0.1700
Data Index: 4458036 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6679. Min Range: -8.6679
Max Act: 7.6679. Min Act: -0.1700
Data Index: 2822580 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19