Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0232. Min Range: -5.0232
Max Act: 5.0232. Min Act: -0.1700
Data Index: 5666608 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.7732. Min Act: -0.1700
Data Index: 1192254 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.7732. Min Act: -0.1700
Data Index: 911934 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.7419. Min Act: -0.1700
Data Index: 5064434 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.7419. Min Act: -0.1700
Data Index: 7149970 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.7419. Min Act: -0.1700
Data Index: 589056 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.7107. Min Act: -0.1700
Data Index: 5920214 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.6169. Min Act: -0.1700
Data Index: 701634 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.6169. Min Act: -0.1700
Data Index: 2024820 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.6169. Min Act: -0.1700
Data Index: 8514185 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.5856. Min Act: -0.1700
Data Index: 5928278 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.5856. Min Act: -0.1700
Data Index: 174673 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.6169. Min Act: -0.1700
Data Index: 3769972 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.5856. Min Act: -0.1700
Data Index: 1672520 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.5544. Min Act: -0.1700
Data Index: 8003704 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.5231. Min Act: -0.1700
Data Index: 6270608 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.5231. Min Act: -0.1700
Data Index: 2485914 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.5231. Min Act: -0.1700
Data Index: 5329404 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.5231. Min Act: -0.1700
Data Index: 5430762 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0232. Min Range: -5.0232
Max Act: 4.5544. Min Act: -0.1700
Data Index: 7539068 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19