Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.9144. Min Act: -0.1700
Data Index: 4881432 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.9144. Min Act: -0.1700
Data Index: 1702968 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.8519. Min Act: -0.1700
Data Index: 4418323 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.8832. Min Act: -0.1700
Data Index: 1079391 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.8207. Min Act: -0.1700
Data Index: 3361223 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.8519. Min Act: -0.1700
Data Index: 6045522 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.7894. Min Act: -0.1700
Data Index: 8813893 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.7894. Min Act: -0.1700
Data Index: 5623783 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.7582. Min Act: -0.1700
Data Index: 7635350 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.7582. Min Act: -0.1700
Data Index: 2689697 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.7582. Min Act: -0.1700
Data Index: 8029 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.6957. Min Act: -0.1700
Data Index: 456591 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.6644. Min Act: -0.1700
Data Index: 2753534 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.6644. Min Act: -0.1700
Data Index: 8660447 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.6644. Min Act: -0.1700
Data Index: 3741183 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.6644. Min Act: -0.1700
Data Index: 7661130 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.6332. Min Act: -0.1700
Data Index: 5731398 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.6644. Min Act: -0.1700
Data Index: 3783101 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.6332. Min Act: -0.1700
Data Index: 7788337 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9144. Min Range: -5.9144
Max Act: 5.6332. Min Act: -0.1700
Data Index: 3694330 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19