Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1221 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0044. Min Range: -7.0044
Max Act: 7.0044. Min Act: -0.1700
Data Index: 2117205 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.5981. Min Act: -0.1700
Data Index: 5535962 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.6294. Min Act: -0.1700
Data Index: 3109258 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.5669. Min Act: -0.1700
Data Index: 6689281 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.5044. Min Act: -0.1700
Data Index: 5881325 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.4106. Min Act: -0.1700
Data Index: 5737956 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.3481. Min Act: -0.1700
Data Index: 5413420 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.3481. Min Act: -0.1700
Data Index: 6577951 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.3169. Min Act: -0.1700
Data Index: 5755804 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.3169. Min Act: -0.1700
Data Index: 281124 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.2856. Min Act: -0.1700
Data Index: 6444338 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.2544. Min Act: -0.1700
Data Index: 4279940 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.2231. Min Act: -0.1700
Data Index: 7683977 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.1919. Min Act: -0.1700
Data Index: 2534119 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.1919. Min Act: -0.1700
Data Index: 2964329 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.1606. Min Act: -0.1700
Data Index: 1082591 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.1919. Min Act: -0.1700
Data Index: 2444574 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.1294. Min Act: -0.1700
Data Index: 4899521 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.0981. Min Act: -0.1700
Data Index: 2964896 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0044. Min Range: -7.0044
Max Act: 6.0981. Min Act: -0.1700
Data Index: 3250697 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19