Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1436. Min Range: -4.1436
Max Act: 4.1436. Min Act: -0.1700
Data Index: 3724157 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1436. Min Range: -4.1436
Max Act: 4.0810. Min Act: -0.1700
Data Index: 1459506 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1436. Min Range: -4.1436
Max Act: 4.0498. Min Act: -0.1700
Data Index: 8570142 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.9873. Min Act: -0.1700
Data Index: 659836 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.9873. Min Act: -0.1700
Data Index: 5791967 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.9560. Min Act: -0.1700
Data Index: 1888939 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.9247. Min Act: -0.1700
Data Index: 8647261 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.8935. Min Act: -0.1700
Data Index: 5038129 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.8935. Min Act: -0.1700
Data Index: 6401989 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.8935. Min Act: -0.1700
Data Index: 5023023 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.8622. Min Act: -0.1700
Data Index: 7524813 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.7997. Min Act: -0.1700
Data Index: 6327661 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.7997. Min Act: -0.1700
Data Index: 2423640 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.7997. Min Act: -0.1700
Data Index: 2083177 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.7684. Min Act: -0.1700
Data Index: 1727316 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.7684. Min Act: -0.1700
Data Index: 3651421 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.7371. Min Act: -0.1700
Data Index: 4802691 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.7684. Min Act: -0.1700
Data Index: 4148974 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.7684. Min Act: -0.1700
Data Index: 6639350 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1436. Min Range: -4.1436
Max Act: 3.7684. Min Act: -0.1700
Data Index: 467288 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19