Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2400 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.3382. Min Act: -0.1700
Data Index: 1640401 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.2132. Min Act: -0.1700
Data Index: 8456652 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.1195. Min Act: -0.1700
Data Index: 5915700 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.1195. Min Act: -0.1700
Data Index: 3886903 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0882. Min Act: -0.1700
Data Index: 4889114 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0570. Min Act: -0.1700
Data Index: 1961453 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0570. Min Act: -0.1700
Data Index: 7984867 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0570. Min Act: -0.1700
Data Index: 121548 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0257. Min Act: -0.1700
Data Index: 3467294 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0257. Min Act: -0.1700
Data Index: 6360040 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0257. Min Act: -0.1700
Data Index: 5434714 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0257. Min Act: -0.1700
Data Index: 6305517 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.9945. Min Act: -0.1700
Data Index: 398460 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0257. Min Act: -0.1700
Data Index: 8453309 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.9945. Min Act: -0.1700
Data Index: 60689 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.9945. Min Act: -0.1700
Data Index: 1596536 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0257. Min Act: -0.1700
Data Index: 6660236 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.9632. Min Act: -0.1700
Data Index: 6895371 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.9320. Min Act: -0.1700
Data Index: 2553911 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.9320. Min Act: -0.1700
Data Index: 2508224 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19