Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.6209. Min Act: -0.1700
Data Index: 5707435 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.5584. Min Act: -0.1700
Data Index: 126684 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.5584. Min Act: -0.1700
Data Index: 5681070 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.5584. Min Act: -0.1700
Data Index: 7438764 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.5272. Min Act: -0.1700
Data Index: 3330717 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.4647. Min Act: -0.1700
Data Index: 2321931 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.4647. Min Act: -0.1700
Data Index: 5666102 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.4334. Min Act: -0.1700
Data Index: 3748407 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.4334. Min Act: -0.1700
Data Index: 6090195 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.4022. Min Act: -0.1700
Data Index: 7616597 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.3709. Min Act: -0.1700
Data Index: 8362020 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.3709. Min Act: -0.1700
Data Index: 5666106 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.3397. Min Act: -0.1700
Data Index: 1279573 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.3709. Min Act: -0.1700
Data Index: 1237402 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.3709. Min Act: -0.1700
Data Index: 7848504 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.3709. Min Act: -0.1700
Data Index: 888449 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.3397. Min Act: -0.1700
Data Index: 3598068 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.3397. Min Act: -0.1700
Data Index: 172909 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.3397. Min Act: -0.1700
Data Index: 2810555 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6209. Min Range: -4.6209
Max Act: 4.3397. Min Act: -0.1700
Data Index: 203139 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19