Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6343 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.7319. Min Act: -0.1700
Data Index: 6415804 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.6694. Min Act: -0.1700
Data Index: 534074 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.4819. Min Act: -0.1700
Data Index: 7013279 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.4506. Min Act: -0.1700
Data Index: 8467462 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.2944. Min Act: -0.1700
Data Index: 8361822 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.2319. Min Act: -0.1700
Data Index: 1776840 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.1381. Min Act: -0.1700
Data Index: 5487266 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.1069. Min Act: -0.1700
Data Index: 6007595 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.0756. Min Act: -0.1700
Data Index: 935257 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.0444. Min Act: -0.1700
Data Index: 4038135 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.0131. Min Act: -0.1700
Data Index: 5822640 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7319. Min Range: -6.7319
Max Act: 6.0131. Min Act: -0.1700
Data Index: 4215754 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7319. Min Range: -6.7319
Max Act: 5.9819. Min Act: -0.1700
Data Index: 4027499 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7319. Min Range: -6.7319
Max Act: 5.9506. Min Act: -0.1700
Data Index: 933698 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7319. Min Range: -6.7319
Max Act: 5.8881. Min Act: -0.1700
Data Index: 2733452 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7319. Min Range: -6.7319
Max Act: 5.8569. Min Act: -0.1700
Data Index: 392118 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7319. Min Range: -6.7319
Max Act: 5.9194. Min Act: -0.1700
Data Index: 4020681 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7319. Min Range: -6.7319
Max Act: 5.8569. Min Act: -0.1700
Data Index: 8000300 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7319. Min Range: -6.7319
Max Act: 5.8256. Min Act: -0.1700
Data Index: 300897 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7319. Min Range: -6.7319
Max Act: 5.8256. Min Act: -0.1700
Data Index: 7963238 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19