Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.9066. Min Act: -0.1700
Data Index: 2579494 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.9066. Min Act: -0.1700
Data Index: 4003341 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.7816. Min Act: -0.1700
Data Index: 2840901 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.7816. Min Act: -0.1700
Data Index: 5288829 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.7816. Min Act: -0.1700
Data Index: 6879360 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.7816. Min Act: -0.1700
Data Index: 6963622 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.7816. Min Act: -0.1700
Data Index: 5592104 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.7191. Min Act: -0.1700
Data Index: 3504046 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.7191. Min Act: -0.1700
Data Index: 8805725 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.6879. Min Act: -0.1700
Data Index: 2381503 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.6879. Min Act: -0.1700
Data Index: 1461763 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.6879. Min Act: -0.1700
Data Index: 4445454 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.6879. Min Act: -0.1700
Data Index: 7997298 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.6879. Min Act: -0.1700
Data Index: 5418651 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.6879. Min Act: -0.1700
Data Index: 89218 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.7191. Min Act: -0.1700
Data Index: 5333892 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.6254. Min Act: -0.1700
Data Index: 5332013 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.6566. Min Act: -0.1700
Data Index: 1621830 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.6254. Min Act: -0.1700
Data Index: 2665103 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9066. Min Range: -4.9066
Max Act: 4.6254. Min Act: -0.1700
Data Index: 6592575 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19