Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.6307. Min Act: -0.1700
Data Index: 4805924 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.3182. Min Act: -0.1700
Data Index: 2308916 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.2557. Min Act: -0.1700
Data Index: 1620751 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.1932. Min Act: -0.1700
Data Index: 4086174 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.0682. Min Act: -0.1700
Data Index: 7892373 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.0682. Min Act: -0.1700
Data Index: 2575467 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.0369. Min Act: -0.1700
Data Index: 6206783 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.0369. Min Act: -0.1700
Data Index: 7245674 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.0057. Min Act: -0.1700
Data Index: 8536590 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6307. Min Range: -6.6307
Max Act: 6.0057. Min Act: -0.1700
Data Index: 2416864 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6307. Min Range: -6.6307
Max Act: 5.9744. Min Act: -0.1700
Data Index: 3909575 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6307. Min Range: -6.6307
Max Act: 5.9432. Min Act: -0.1700
Data Index: 7294252 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6307. Min Range: -6.6307
Max Act: 5.9432. Min Act: -0.1700
Data Index: 4681850 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6307. Min Range: -6.6307
Max Act: 5.9119. Min Act: -0.1700
Data Index: 5579450 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6307. Min Range: -6.6307
Max Act: 5.9119. Min Act: -0.1700
Data Index: 1865242 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6307. Min Range: -6.6307
Max Act: 5.9119. Min Act: -0.1700
Data Index: 4037314 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6307. Min Range: -6.6307
Max Act: 5.8494. Min Act: -0.1700
Data Index: 6225530 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6307. Min Range: -6.6307
Max Act: 5.8494. Min Act: -0.1700
Data Index: 3864870 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6307. Min Range: -6.6307
Max Act: 5.8494. Min Act: -0.1700
Data Index: 2068976 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6307. Min Range: -6.6307
Max Act: 5.8494. Min Act: -0.1700
Data Index: 1165309 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19