Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.9807. Min Act: -0.1700
Data Index: 4428467 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.8557. Min Act: -0.1700
Data Index: 5841421 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.8557. Min Act: -0.1700
Data Index: 4628100 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.6682. Min Act: -0.1700
Data Index: 6125990 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.6682. Min Act: -0.1700
Data Index: 4869246 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.6682. Min Act: -0.1700
Data Index: 5625008 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.5432. Min Act: -0.1700
Data Index: 4288133 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.5120. Min Act: -0.1700
Data Index: 6806683 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.4807. Min Act: -0.1700
Data Index: 7433285 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.4807. Min Act: -0.1700
Data Index: 3125909 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.4182. Min Act: -0.1700
Data Index: 1320854 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.4807. Min Act: -0.1700
Data Index: 3572329 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.3870. Min Act: -0.1700
Data Index: 5641221 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.3870. Min Act: -0.1700
Data Index: 815660 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.3245. Min Act: -0.1700
Data Index: 1000218 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.2932. Min Act: -0.1700
Data Index: 8583002 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.2932. Min Act: -0.1700
Data Index: 4288131 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.2620. Min Act: -0.1700
Data Index: 5808065 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.1995. Min Act: -0.1700
Data Index: 782007 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9807. Min Range: -7.9807
Max Act: 7.2620. Min Act: -0.1700
Data Index: 468484 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19