Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.4131. Min Act: -0.1700
Data Index: 6217087 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.3194. Min Act: -0.1700
Data Index: 7676974 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.2881. Min Act: -0.1700
Data Index: 2099445 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.2569. Min Act: -0.1700
Data Index: 8188503 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.2256. Min Act: -0.1700
Data Index: 3264569 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.1944. Min Act: -0.1700
Data Index: 8118721 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.1631. Min Act: -0.1700
Data Index: 8662937 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.1319. Min Act: -0.1700
Data Index: 8625989 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.1319. Min Act: -0.1700
Data Index: 5636568 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.0069. Min Act: -0.1700
Data Index: 4220457 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.0069. Min Act: -0.1700
Data Index: 8748073 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.0069. Min Act: -0.1700
Data Index: 7526779 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4131. Min Range: -7.4131
Max Act: 7.0069. Min Act: -0.1700
Data Index: 309261 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4131. Min Range: -7.4131
Max Act: 6.9444. Min Act: -0.1700
Data Index: 6722987 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4131. Min Range: -7.4131
Max Act: 6.9444. Min Act: -0.1700
Data Index: 4321106 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4131. Min Range: -7.4131
Max Act: 6.9131. Min Act: -0.1700
Data Index: 8359464 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4131. Min Range: -7.4131
Max Act: 6.9131. Min Act: -0.1700
Data Index: 5653200 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4131. Min Range: -7.4131
Max Act: 6.9131. Min Act: -0.1700
Data Index: 1747380 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4131. Min Range: -7.4131
Max Act: 6.8819. Min Act: -0.1700
Data Index: 693119 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4131. Min Range: -7.4131
Max Act: 6.8506. Min Act: -0.1700
Data Index: 1999857 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19