Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.5623. Min Act: -0.1700
Data Index: 5804922 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.4998. Min Act: -0.1700
Data Index: 5670148 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.4373. Min Act: -0.1700
Data Index: 1901715 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.3123. Min Act: -0.1700
Data Index: 6466515 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.3123. Min Act: -0.1700
Data Index: 4721830 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.2810. Min Act: -0.1700
Data Index: 5724431 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.1560. Min Act: -0.1700
Data Index: 5709019 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0935. Min Act: -0.1700
Data Index: 4969511 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0935. Min Act: -0.1700
Data Index: 1474967 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0623. Min Act: -0.1700
Data Index: 6495413 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0623. Min Act: -0.1700
Data Index: 4230739 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0935. Min Act: -0.1700
Data Index: 2893853 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0310. Min Act: -0.1700
Data Index: 6071774 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0310. Min Act: -0.1700
Data Index: 1205673 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.9998. Min Act: -0.1700
Data Index: 8703103 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.9998. Min Act: -0.1700
Data Index: 6466517 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5623. Min Range: -7.5623
Max Act: 7.0310. Min Act: -0.1700
Data Index: 2456507 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.9685. Min Act: -0.1700
Data Index: 5201546 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.9685. Min Act: -0.1700
Data Index: 8140437 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5623. Min Range: -7.5623
Max Act: 6.9373. Min Act: -0.1700
Data Index: 4190507 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19