Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2172 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.4397. Min Act: -0.1700
Data Index: 4832187 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.4084. Min Act: -0.1700
Data Index: 4879101 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.3927. Min Act: -0.1700
Data Index: 2880192 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.3457. Min Act: -0.1700
Data Index: 3509772 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.3143. Min Act: -0.1700
Data Index: 389442 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.3300. Min Act: -0.1700
Data Index: 1996876 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.3300. Min Act: -0.1700
Data Index: 1818126 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.3143. Min Act: -0.1700
Data Index: 4722273 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2986. Min Act: -0.1700
Data Index: 4373028 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2672. Min Act: -0.1700
Data Index: 4683149 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2829. Min Act: -0.1700
Data Index: 2588906 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2829. Min Act: -0.1700
Data Index: 3910230 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2672. Min Act: -0.1700
Data Index: 586183 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2515. Min Act: -0.1700
Data Index: 7360908 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2515. Min Act: -0.1700
Data Index: 3520967 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2515. Min Act: -0.1700
Data Index: 3273439 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2515. Min Act: -0.1700
Data Index: 8255214 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2357. Min Act: -0.1700
Data Index: 1930847 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2043. Min Act: -0.1700
Data Index: 3961245 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4397. Min Range: -3.4397
Max Act: 3.2043. Min Act: -0.1700
Data Index: 7273145 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19