Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 953 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.8064. Min Act: -0.1700
Data Index: 2221937 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.5877. Min Act: -0.1700
Data Index: 520467 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.5252. Min Act: -0.1700
Data Index: 5448218 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.4939. Min Act: -0.1700
Data Index: 694847 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.4939. Min Act: -0.1700
Data Index: 455615 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.4002. Min Act: -0.1700
Data Index: 2940814 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.4002. Min Act: -0.1700
Data Index: 8831542 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.3689. Min Act: -0.1700
Data Index: 1813125 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.3064. Min Act: -0.1700
Data Index: 6632994 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.3689. Min Act: -0.1700
Data Index: 4544910 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.3377. Min Act: -0.1700
Data Index: 6256139 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.3064. Min Act: -0.1700
Data Index: 4671189 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.3064. Min Act: -0.1700
Data Index: 1057789 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.2752. Min Act: -0.1700
Data Index: 4622614 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.2752. Min Act: -0.1700
Data Index: 493265 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.2439. Min Act: -0.1700
Data Index: 2073139 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.2439. Min Act: -0.1700
Data Index: 996637 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.2127. Min Act: -0.1700
Data Index: 1619928 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.2127. Min Act: -0.1700
Data Index: 2324250 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8064. Min Range: -5.8064
Max Act: 5.2127. Min Act: -0.1700
Data Index: 5669810 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19