Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4337. Min Range: -7.4337
Max Act: 7.4337. Min Act: -0.1700
Data Index: 5865825 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4337. Min Range: -7.4337
Max Act: 7.2150. Min Act: -0.1700
Data Index: 5217278 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.9962. Min Act: -0.1700
Data Index: 6065593 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.9650. Min Act: -0.1700
Data Index: 7945899 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.9025. Min Act: -0.1700
Data Index: 3911547 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.8712. Min Act: -0.1700
Data Index: 8739043 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.8712. Min Act: -0.1700
Data Index: 1384937 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.8400. Min Act: -0.1700
Data Index: 8593504 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.8087. Min Act: -0.1700
Data Index: 5454105 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.7775. Min Act: -0.1700
Data Index: 5621299 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.7775. Min Act: -0.1700
Data Index: 1302762 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.7462. Min Act: -0.1700
Data Index: 8777657 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.7150. Min Act: -0.1700
Data Index: 1502315 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.7462. Min Act: -0.1700
Data Index: 6291917 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.6837. Min Act: -0.1700
Data Index: 7852354 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.6837. Min Act: -0.1700
Data Index: 5118116 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.6837. Min Act: -0.1700
Data Index: 7364714 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.6837. Min Act: -0.1700
Data Index: 930235 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.6525. Min Act: -0.1700
Data Index: 1328513 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4337. Min Range: -7.4337
Max Act: 6.6212. Min Act: -0.1700
Data Index: 6333638 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19