Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 870 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.9331. Min Act: -0.1700
Data Index: 1334754 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.7769. Min Act: -0.1700
Data Index: 7359679 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.6831. Min Act: -0.1700
Data Index: 3426351 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.6206. Min Act: -0.1700
Data Index: 7610455 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.6206. Min Act: -0.1700
Data Index: 3465846 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.5894. Min Act: -0.1700
Data Index: 5990750 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.4956. Min Act: -0.1700
Data Index: 24126 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.4956. Min Act: -0.1700
Data Index: 7214535 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.4644. Min Act: -0.1700
Data Index: 2012212 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.4331. Min Act: -0.1700
Data Index: 1719799 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.4331. Min Act: -0.1700
Data Index: 634714 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.4019. Min Act: -0.1700
Data Index: 5036149 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.4019. Min Act: -0.1700
Data Index: 783738 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.3706. Min Act: -0.1700
Data Index: 1271506 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.3394. Min Act: -0.1700
Data Index: 974198 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.3081. Min Act: -0.1700
Data Index: 8647868 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.3394. Min Act: -0.1700
Data Index: 4143339 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.2769. Min Act: -0.1700
Data Index: 1499738 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.2769. Min Act: -0.1700
Data Index: 3015356 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9331. Min Range: -7.9331
Max Act: 7.2769. Min Act: -0.1700
Data Index: 1090854 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19