Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4741 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.3974. Min Act: -0.1700
Data Index: 4441376 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.3974. Min Act: -0.1700
Data Index: 3975446 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.3503. Min Act: -0.1700
Data Index: 276692 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.3346. Min Act: -0.1700
Data Index: 8519602 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.3033. Min Act: -0.1700
Data Index: 3414801 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.3033. Min Act: -0.1700
Data Index: 180426 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2876. Min Act: -0.1700
Data Index: 6675710 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2876. Min Act: -0.1700
Data Index: 7169839 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2719. Min Act: -0.1700
Data Index: 3520934 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2404. Min Act: -0.1700
Data Index: 568971 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2561. Min Act: -0.1700
Data Index: 1331455 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2561. Min Act: -0.1700
Data Index: 7322028 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2404. Min Act: -0.1700
Data Index: 1742603 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2404. Min Act: -0.1700
Data Index: 1741729 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2404. Min Act: -0.1700
Data Index: 2018018 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2404. Min Act: -0.1700
Data Index: 2399677 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2404. Min Act: -0.1700
Data Index: 2903941 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2561. Min Act: -0.1700
Data Index: 1155576 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2404. Min Act: -0.1700
Data Index: 6059948 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3974. Min Range: -3.3974
Max Act: 3.2090. Min Act: -0.1700
Data Index: 4146452 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19