Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5162 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0505. Min Range: -5.0505
Max Act: 5.0505. Min Act: -0.1700
Data Index: 639447 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0505. Min Range: -5.0505
Max Act: 5.0192. Min Act: -0.1700
Data Index: 8373383 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.8942. Min Act: -0.1700
Data Index: 6574385 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.8630. Min Act: -0.1700
Data Index: 319797 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.8630. Min Act: -0.1700
Data Index: 319800 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.8630. Min Act: -0.1700
Data Index: 3442006 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.8630. Min Act: -0.1700
Data Index: 319805 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.8005. Min Act: -0.1700
Data Index: 6411010 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.8005. Min Act: -0.1700
Data Index: 5800988 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.8005. Min Act: -0.1700
Data Index: 319793 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.8005. Min Act: -0.1700
Data Index: 3125118 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.7692. Min Act: -0.1700
Data Index: 4897370 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.7380. Min Act: -0.1700
Data Index: 319803 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.6755. Min Act: -0.1700
Data Index: 1081147 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.6755. Min Act: -0.1700
Data Index: 4039887 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.6755. Min Act: -0.1700
Data Index: 5623638 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.6442. Min Act: -0.1700
Data Index: 4255695 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.6442. Min Act: -0.1700
Data Index: 1081140 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.6130. Min Act: -0.1700
Data Index: 3104484 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0505. Min Range: -5.0505
Max Act: 4.6130. Min Act: -0.1700
Data Index: 5921719 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19