Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1719 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.7783. Min Act: -0.1700
Data Index: 7013288 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.5283. Min Act: -0.1700
Data Index: 4435451 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.5908. Min Act: -0.1700
Data Index: 3683996 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.5283. Min Act: -0.1700
Data Index: 6429864 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.5283. Min Act: -0.1700
Data Index: 61882 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.5283. Min Act: -0.1700
Data Index: 5042653 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.4658. Min Act: -0.1700
Data Index: 7013283 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.4658. Min Act: -0.1700
Data Index: 4387872 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.4033. Min Act: -0.1700
Data Index: 8229555 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.3408. Min Act: -0.1700
Data Index: 6402871 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.2783. Min Act: -0.1700
Data Index: 3337451 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.2783. Min Act: -0.1700
Data Index: 6109060 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.3408. Min Act: -0.1700
Data Index: 8315284 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.2783. Min Act: -0.1700
Data Index: 3930499 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.2783. Min Act: -0.1700
Data Index: 701089 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.2783. Min Act: -0.1700
Data Index: 1418478 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.2158. Min Act: -0.1700
Data Index: 705655 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.2158. Min Act: -0.1700
Data Index: 6605133 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.2158. Min Act: -0.1700
Data Index: 7014560 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7783. Min Range: -9.7783
Max Act: 9.2158. Min Act: -0.1700
Data Index: 7089576 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19