Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3662 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0161. Min Range: -5.0161
Max Act: 5.0161. Min Act: -0.1700
Data Index: 7016610 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.9849. Min Act: -0.1700
Data Index: 4639826 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.9849. Min Act: -0.1700
Data Index: 5007055 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.9536. Min Act: -0.1700
Data Index: 526625 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.9224. Min Act: -0.1700
Data Index: 1115780 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.8911. Min Act: -0.1700
Data Index: 3616295 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.8599. Min Act: -0.1700
Data Index: 6062270 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.8599. Min Act: -0.1700
Data Index: 5507513 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.8599. Min Act: -0.1700
Data Index: 6740520 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.8599. Min Act: -0.1700
Data Index: 5007054 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7036. Min Act: -0.1700
Data Index: 8125213 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7036. Min Act: -0.1700
Data Index: 3568854 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7036. Min Act: -0.1700
Data Index: 7549466 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.7036. Min Act: -0.1700
Data Index: 1387645 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.6724. Min Act: -0.1700
Data Index: 7129750 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.6411. Min Act: -0.1700
Data Index: 8817554 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.6099. Min Act: -0.1700
Data Index: 74230 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.5474. Min Act: -0.1700
Data Index: 3043060 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.5161. Min Act: -0.1700
Data Index: 1273713 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0161. Min Range: -5.0161
Max Act: 4.4849. Min Act: -0.1700
Data Index: 5401112 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19