Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1410 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.5623. Min Act: -0.1700
Data Index: 627198 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.4373. Min Act: -0.1700
Data Index: 627197 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.2810. Min Act: -0.1700
Data Index: 2560120 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.2185. Min Act: -0.1700
Data Index: 7998631 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.2185. Min Act: -0.1700
Data Index: 627200 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.2185. Min Act: -0.1700
Data Index: 2560114 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0935. Min Act: -0.1700
Data Index: 6063667 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0623. Min Act: -0.1700
Data Index: 1931718 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0623. Min Act: -0.1700
Data Index: 6303791 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0623. Min Act: -0.1700
Data Index: 2560132 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0310. Min Act: -0.1700
Data Index: 2560129 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0310. Min Act: -0.1700
Data Index: 2560131 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0623. Min Act: -0.1700
Data Index: 2560113 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.9998. Min Act: -0.1700
Data Index: 627194 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.9685. Min Act: -0.1700
Data Index: 2560124 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.9373. Min Act: -0.1700
Data Index: 2560123 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.9060. Min Act: -0.1700
Data Index: 2522645 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.9060. Min Act: -0.1700
Data Index: 5289805 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.9060. Min Act: -0.1700
Data Index: 2560121 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.8748. Min Act: -0.1700
Data Index: 627202 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19