Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7146. Min Range: -7.7146
Max Act: 7.7146. Min Act: -0.1700
Data Index: 5430379 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.9021. Min Act: -0.1700
Data Index: 3979669 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.8083. Min Act: -0.1700
Data Index: 7989147 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.7458. Min Act: -0.1700
Data Index: 5393150 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.7146. Min Act: -0.1700
Data Index: 6009228 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.5896. Min Act: -0.1700
Data Index: 2368711 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.5583. Min Act: -0.1700
Data Index: 454587 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.5896. Min Act: -0.1700
Data Index: 381370 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.5271. Min Act: -0.1700
Data Index: 7987206 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.5271. Min Act: -0.1700
Data Index: 6579141 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.4958. Min Act: -0.1700
Data Index: 6556525 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.4958. Min Act: -0.1700
Data Index: 5976225 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.4333. Min Act: -0.1700
Data Index: 1554546 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.4333. Min Act: -0.1700
Data Index: 5606401 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.4333. Min Act: -0.1700
Data Index: 1317541 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.4333. Min Act: -0.1700
Data Index: 8753007 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.4333. Min Act: -0.1700
Data Index: 7926101 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.3708. Min Act: -0.1700
Data Index: 6999519 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.3708. Min Act: -0.1700
Data Index: 971418 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7146. Min Range: -7.7146
Max Act: 6.3708. Min Act: -0.1700
Data Index: 7928298 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19