Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4413 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0113. Min Range: -3.0113
Max Act: 3.0113. Min Act: -0.1700
Data Index: 5086618 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.8210. Min Act: -0.1700
Data Index: 7748069 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.8051. Min Act: -0.1700
Data Index: 5407379 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.7733. Min Act: -0.1700
Data Index: 8195506 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.7573. Min Act: -0.1700
Data Index: 6896869 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.7414. Min Act: -0.1700
Data Index: 540186 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.7094. Min Act: -0.1700
Data Index: 5453247 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.7094. Min Act: -0.1700
Data Index: 3716811 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.6613. Min Act: -0.1700
Data Index: 5836944 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.6774. Min Act: -0.1700
Data Index: 1358491 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.6613. Min Act: -0.1700
Data Index: 3902383 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.6453. Min Act: -0.1700
Data Index: 3413190 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.6292. Min Act: -0.1700
Data Index: 7611629 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.6132. Min Act: -0.1700
Data Index: 5929024 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.6292. Min Act: -0.1700
Data Index: 1707614 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.6132. Min Act: -0.1700
Data Index: 5508069 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.6132. Min Act: -0.1700
Data Index: 3902384 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.5971. Min Act: -0.1700
Data Index: 4545924 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.6132. Min Act: -0.1700
Data Index: 6288740 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0113. Min Range: -3.0113
Max Act: 2.5971. Min Act: -0.1700
Data Index: 7706701 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19