Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3315 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0711. Min Range: -9.0711
Max Act: 9.0711. Min Act: -0.1700
Data Index: 8824409 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0711. Min Range: -9.0711
Max Act: 9.0086. Min Act: -0.1700
Data Index: 7231938 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.6336. Min Act: -0.1700
Data Index: 2134463 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.5086. Min Act: -0.1700
Data Index: 1775478 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.4461. Min Act: -0.1700
Data Index: 5998100 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.4461. Min Act: -0.1700
Data Index: 3594572 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.5086. Min Act: -0.1700
Data Index: 3124635 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.4461. Min Act: -0.1700
Data Index: 6520727 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.3836. Min Act: -0.1700
Data Index: 231749 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.2586. Min Act: -0.1700
Data Index: 1001185 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.3211. Min Act: -0.1700
Data Index: 2443644 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.2586. Min Act: -0.1700
Data Index: 5142533 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.2586. Min Act: -0.1700
Data Index: 4129878 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.2586. Min Act: -0.1700
Data Index: 8307301 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.1336. Min Act: -0.1700
Data Index: 802217 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.1961. Min Act: -0.1700
Data Index: 6762852 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.1961. Min Act: -0.1700
Data Index: 5274397 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.1961. Min Act: -0.1700
Data Index: 4314827 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.1961. Min Act: -0.1700
Data Index: 7781656 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0711. Min Range: -9.0711
Max Act: 8.1961. Min Act: -0.1700
Data Index: 5672531 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19