Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1437 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.7658. Min Act: -0.1700
Data Index: 4510867 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.6408. Min Act: -0.1700
Data Index: 4232303 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.5158. Min Act: -0.1700
Data Index: 6109277 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.5158. Min Act: -0.1700
Data Index: 373157 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.5158. Min Act: -0.1700
Data Index: 5522833 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.4845. Min Act: -0.1700
Data Index: 2269527 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.4220. Min Act: -0.1700
Data Index: 844296 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.3908. Min Act: -0.1700
Data Index: 455757 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.3595. Min Act: -0.1700
Data Index: 6571066 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.3595. Min Act: -0.1700
Data Index: 2693112 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.3595. Min Act: -0.1700
Data Index: 6850966 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.3595. Min Act: -0.1700
Data Index: 2358502 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.3283. Min Act: -0.1700
Data Index: 4447887 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.3283. Min Act: -0.1700
Data Index: 5188270 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.3283. Min Act: -0.1700
Data Index: 2108770 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.2970. Min Act: -0.1700
Data Index: 7354567 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.2658. Min Act: -0.1700
Data Index: 3529812 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.2970. Min Act: -0.1700
Data Index: 1117955 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.2345. Min Act: -0.1700
Data Index: 1331078 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7658. Min Range: -5.7658
Max Act: 5.2345. Min Act: -0.1700
Data Index: 5500227 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19