Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.6459. Min Act: -0.1700
Data Index: 4639512 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.6459. Min Act: -0.1700
Data Index: 5344149 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.6459. Min Act: -0.1700
Data Index: 5799021 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.6146. Min Act: -0.1700
Data Index: 4450854 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.5521. Min Act: -0.1700
Data Index: 5086664 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.5834. Min Act: -0.1700
Data Index: 4969104 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.5521. Min Act: -0.1700
Data Index: 2545280 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.5521. Min Act: -0.1700
Data Index: 4969111 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.5521. Min Act: -0.1700
Data Index: 7296034 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.4896. Min Act: -0.1700
Data Index: 7405110 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.4584. Min Act: -0.1700
Data Index: 7521453 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.4584. Min Act: -0.1700
Data Index: 7405109 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.4584. Min Act: -0.1700
Data Index: 6562021 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.4271. Min Act: -0.1700
Data Index: 3753988 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.4271. Min Act: -0.1700
Data Index: 2385073 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.4271. Min Act: -0.1700
Data Index: 617510 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.4271. Min Act: -0.1700
Data Index: 7438725 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.4271. Min Act: -0.1700
Data Index: 5262686 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.3959. Min Act: -0.1700
Data Index: 3766410 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6459. Min Range: -7.6459
Max Act: 7.3959. Min Act: -0.1700
Data Index: 1187629 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19