Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2717 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.7146. Min Act: -0.1700
Data Index: 6624773 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.7458. Min Act: -0.1700
Data Index: 1924238 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.6208. Min Act: -0.1700
Data Index: 1267161 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.6208. Min Act: -0.1700
Data Index: 6284252 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.5271. Min Act: -0.1700
Data Index: 6284253 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.5583. Min Act: -0.1700
Data Index: 8211294 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.5271. Min Act: -0.1700
Data Index: 5970878 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.5271. Min Act: -0.1700
Data Index: 6841113 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.5583. Min Act: -0.1700
Data Index: 6598473 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.5271. Min Act: -0.1700
Data Index: 179074 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.4958. Min Act: -0.1700
Data Index: 4201873 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.4646. Min Act: -0.1700
Data Index: 3816907 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.4646. Min Act: -0.1700
Data Index: 4651155 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.4333. Min Act: -0.1700
Data Index: 7023671 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.4646. Min Act: -0.1700
Data Index: 8106959 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.4021. Min Act: -0.1700
Data Index: 5903278 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.4021. Min Act: -0.1700
Data Index: 255644 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.4021. Min Act: -0.1700
Data Index: 1984640 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.4021. Min Act: -0.1700
Data Index: 3488821 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7458. Min Range: -4.7458
Max Act: 4.4021. Min Act: -0.1700
Data Index: 6508668 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19