Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5259 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.8358. Min Act: -0.1700
Data Index: 8458784 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.6483. Min Act: -0.1700
Data Index: 6242397 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.6170. Min Act: -0.1700
Data Index: 6772217 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.5858. Min Act: -0.1700
Data Index: 3133585 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.5858. Min Act: -0.1699
Data Index: 948184 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.5233. Min Act: -0.1700
Data Index: 4080254 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.4608. Min Act: -0.1700
Data Index: 1195217 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3983. Min Act: -0.1700
Data Index: 1360090 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.4295. Min Act: -0.1700
Data Index: 5246764 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3983. Min Act: -0.1700
Data Index: 6390090 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3983. Min Act: -0.1700
Data Index: 6561136 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3983. Min Act: -0.1700
Data Index: 8337200 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3670. Min Act: -0.1700
Data Index: 1550747 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3670. Min Act: -0.1700
Data Index: 8383832 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3670. Min Act: -0.1700
Data Index: 7419617 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3670. Min Act: -0.1700
Data Index: 196796 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3358. Min Act: -0.1700
Data Index: 7901132 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3358. Min Act: -0.1700
Data Index: 7143368 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3358. Min Act: -0.1700
Data Index: 4424265 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8358. Min Range: -4.8358
Max Act: 4.3358. Min Act: -0.1700
Data Index: 4238228 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19