Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.5873. Min Act: -0.1700
Data Index: 3433063 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4936. Min Act: -0.1700
Data Index: 319707 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4623. Min Act: -0.1700
Data Index: 6423542 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4936. Min Act: -0.1700
Data Index: 7361468 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4936. Min Act: -0.1700
Data Index: 5262876 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.5248. Min Act: -0.1699
Data Index: 7292402 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4623. Min Act: -0.1700
Data Index: 2357799 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4623. Min Act: -0.1700
Data Index: 3371103 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4311. Min Act: -0.1700
Data Index: 8208912 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4311. Min Act: -0.1700
Data Index: 1240171 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4311. Min Act: -0.1700
Data Index: 6310320 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4311. Min Act: -0.1700
Data Index: 7584804 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4311. Min Act: -0.1700
Data Index: 1456098 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.3998. Min Act: -0.1700
Data Index: 632043 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.3998. Min Act: -0.1700
Data Index: 2966850 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.3998. Min Act: -0.1700
Data Index: 4209409 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.3686. Min Act: -0.1700
Data Index: 4012624 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.3998. Min Act: -0.1700
Data Index: 1899007 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.4311. Min Act: -0.1700
Data Index: 7280278 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5873. Min Range: -5.5873
Max Act: 5.3998. Min Act: -0.1700
Data Index: 6217068 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19