Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0147. Min Range: -7.0147
Max Act: 7.0147. Min Act: -0.1700
Data Index: 1345051 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.9522. Min Act: -0.1700
Data Index: 982138 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.8272. Min Act: -0.1700
Data Index: 67079 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.8272. Min Act: -0.1700
Data Index: 3346750 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7960. Min Act: -0.1700
Data Index: 8442537 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7960. Min Act: -0.1700
Data Index: 1473274 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7647. Min Act: -0.1700
Data Index: 1875148 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7647. Min Act: -0.1700
Data Index: 7365276 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7647. Min Act: -0.1700
Data Index: 415639 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7647. Min Act: -0.1700
Data Index: 6221550 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7022. Min Act: -0.1700
Data Index: 6661909 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7335. Min Act: -0.1700
Data Index: 2181763 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7022. Min Act: -0.1700
Data Index: 2902277 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7335. Min Act: -0.1700
Data Index: 3600629 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7022. Min Act: -0.1700
Data Index: 894147 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7022. Min Act: -0.1700
Data Index: 5558851 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.7022. Min Act: -0.1700
Data Index: 5339638 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.6397. Min Act: -0.1700
Data Index: 1345054 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.6397. Min Act: -0.1700
Data Index: 1571959 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0147. Min Range: -7.0147
Max Act: 6.6397. Min Act: -0.1700
Data Index: 2310335 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19