Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5931 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.8319. Min Act: -0.1700
Data Index: 7651574 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.7381. Min Act: -0.1700
Data Index: 1569185 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.6444. Min Act: -0.1700
Data Index: 6876164 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.6131. Min Act: -0.1700
Data Index: 1150098 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5819. Min Act: -0.1700
Data Index: 7827146 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5819. Min Act: -0.1700
Data Index: 1360020 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5194. Min Act: -0.1700
Data Index: 7535276 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4569. Min Act: -0.1700
Data Index: 5748076 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4881. Min Act: -0.1700
Data Index: 636306 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4881. Min Act: -0.1700
Data Index: 3668465 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4569. Min Act: -0.1700
Data Index: 5901463 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4569. Min Act: -0.1700
Data Index: 5312050 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4569. Min Act: -0.1700
Data Index: 4879894 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4569. Min Act: -0.1700
Data Index: 103643 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4256. Min Act: -0.1700
Data Index: 7850418 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4256. Min Act: -0.1700
Data Index: 91350 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.3944. Min Act: -0.1700
Data Index: 8080579 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.3944. Min Act: -0.1700
Data Index: 3357029 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.3944. Min Act: -0.1700
Data Index: 4298948 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.3944. Min Act: -0.1700
Data Index: 7008726 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19