Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1522. Min Range: -6.1522
Max Act: 6.1522. Min Act: -0.1700
Data Index: 7416324 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1522. Min Range: -6.1522
Max Act: 6.0897. Min Act: -0.1700
Data Index: 371743 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.9960. Min Act: -0.1700
Data Index: 513996 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.9335. Min Act: -0.1700
Data Index: 907985 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.9022. Min Act: -0.1700
Data Index: 6985471 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.9022. Min Act: -0.1700
Data Index: 8696559 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.8710. Min Act: -0.1700
Data Index: 3831412 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.8397. Min Act: -0.1700
Data Index: 4829470 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.8397. Min Act: -0.1700
Data Index: 5589825 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.8397. Min Act: -0.1700
Data Index: 165174 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.8085. Min Act: -0.1700
Data Index: 3820794 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.8085. Min Act: -0.1700
Data Index: 5943316 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.8397. Min Act: -0.1700
Data Index: 5890598 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.8085. Min Act: -0.1700
Data Index: 8806414 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.8085. Min Act: -0.1700
Data Index: 7346903 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.7772. Min Act: -0.1700
Data Index: 2413187 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.7772. Min Act: -0.1700
Data Index: 6108952 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.7772. Min Act: -0.1700
Data Index: 4487195 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.7772. Min Act: -0.1700
Data Index: 6407370 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1522. Min Range: -6.1522
Max Act: 5.7772. Min Act: -0.1700
Data Index: 6634097 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19