Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3752 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.3319. Min Range: -10.3319
Max Act: 10.3319. Min Act: -0.1700
Data Index: 3028861 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3319. Min Range: -10.3319
Max Act: 10.1444. Min Act: -0.1700
Data Index: 4408195 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.9569. Min Act: -0.1700
Data Index: 527400 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.8944. Min Act: -0.1699
Data Index: 8118487 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.8944. Min Act: -0.1700
Data Index: 8029596 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.8319. Min Act: -0.1700
Data Index: 1023159 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.8319. Min Act: -0.1700
Data Index: 945683 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.8944. Min Act: -0.1700
Data Index: 8001924 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.8944. Min Act: -0.1699
Data Index: 7823545 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.7694. Min Act: -0.1700
Data Index: 4536620 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.7694. Min Act: -0.1700
Data Index: 4571590 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.8319. Min Act: -0.1700
Data Index: 6408142 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.7069. Min Act: -0.1700
Data Index: 5255600 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.7069. Min Act: -0.1700
Data Index: 8094391 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.6444. Min Act: -0.1700
Data Index: 6887312 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.6444. Min Act: -0.1700
Data Index: 3978874 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.7069. Min Act: -0.1700
Data Index: 2791456 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.6444. Min Act: -0.1699
Data Index: 4896181 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.6444. Min Act: -0.1700
Data Index: 3790424 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3319. Min Range: -10.3319
Max Act: 9.6444. Min Act: -0.1700
Data Index: 5395405 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19