Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.5903. Min Act: -0.1700
Data Index: 4716969 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.5746. Min Act: -0.1700
Data Index: 6612011 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.5276. Min Act: -0.1700
Data Index: 91203 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.5120. Min Act: -0.1700
Data Index: 5978490 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.4807. Min Act: -0.1700
Data Index: 683066 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.4807. Min Act: -0.1700
Data Index: 7111545 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.4807. Min Act: -0.1700
Data Index: 4048124 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.4650. Min Act: -0.1700
Data Index: 5900236 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.4807. Min Act: -0.1700
Data Index: 3608868 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.4650. Min Act: -0.1700
Data Index: 4523757 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.4336. Min Act: -0.1700
Data Index: 1146824 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.4336. Min Act: -0.1700
Data Index: 3018484 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.4336. Min Act: -0.1700
Data Index: 6169620 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.4180. Min Act: -0.1700
Data Index: 3604164 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.3866. Min Act: -0.1700
Data Index: 4782928 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.3866. Min Act: -0.1700
Data Index: 1764419 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.3866. Min Act: -0.1700
Data Index: 998853 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.3709. Min Act: -0.1700
Data Index: 5161721 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.3552. Min Act: -0.1700
Data Index: 1239262 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5903. Min Range: -3.5903
Max Act: 3.3709. Min Act: -0.1700
Data Index: 1907713 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19