Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4489 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1461. Min Range: -8.1461
Max Act: 8.1461. Min Act: -0.1700
Data Index: 7789906 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1461. Min Range: -8.1461
Max Act: 8.1461. Min Act: -0.1700
Data Index: 1481011 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1461. Min Range: -8.1461
Max Act: 8.0211. Min Act: -0.1700
Data Index: 7630228 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1461. Min Range: -8.1461
Max Act: 8.0211. Min Act: -0.1700
Data Index: 4468253 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.8648. Min Act: -0.1700
Data Index: 5092747 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.8023. Min Act: -0.1700
Data Index: 1003551 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.8023. Min Act: -0.1700
Data Index: 5402394 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.7711. Min Act: -0.1700
Data Index: 6037265 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.7086. Min Act: -0.1700
Data Index: 8320218 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.7086. Min Act: -0.1700
Data Index: 2250959 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.7086. Min Act: -0.1700
Data Index: 2943980 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.7086. Min Act: -0.1700
Data Index: 1296831 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.6773. Min Act: -0.1700
Data Index: 1619360 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.6461. Min Act: -0.1700
Data Index: 1999246 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.6461. Min Act: -0.1700
Data Index: 7313852 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.6461. Min Act: -0.1700
Data Index: 6028921 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.5836. Min Act: -0.1700
Data Index: 1913475 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.5523. Min Act: -0.1700
Data Index: 3290193 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.5523. Min Act: -0.1700
Data Index: 5214468 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1461. Min Range: -8.1461
Max Act: 7.5211. Min Act: -0.1700
Data Index: 5586972 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19