Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.3591. Min Act: -0.1700
Data Index: 4834808 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.3279. Min Act: -0.1700
Data Index: 8593147 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.2029. Min Act: -0.1700
Data Index: 4488849 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.2029. Min Act: -0.1700
Data Index: 844054 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.2029. Min Act: -0.1700
Data Index: 881225 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.2029. Min Act: -0.1700
Data Index: 2734984 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.1404. Min Act: -0.1700
Data Index: 8724750 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.1404. Min Act: -0.1700
Data Index: 476167 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.1404. Min Act: -0.1700
Data Index: 4771189 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.1091. Min Act: -0.1700
Data Index: 2725621 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.0779. Min Act: -0.1700
Data Index: 4320843 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.0466. Min Act: -0.1700
Data Index: 3240019 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.0466. Min Act: -0.1700
Data Index: 2245331 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3591. Min Range: -6.3591
Max Act: 6.0154. Min Act: -0.1700
Data Index: 2545597 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3591. Min Range: -6.3591
Max Act: 5.9841. Min Act: -0.1700
Data Index: 2562668 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3591. Min Range: -6.3591
Max Act: 5.9529. Min Act: -0.1700
Data Index: 4890110 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3591. Min Range: -6.3591
Max Act: 5.9841. Min Act: -0.1700
Data Index: 2182532 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3591. Min Range: -6.3591
Max Act: 5.9216. Min Act: -0.1700
Data Index: 1364665 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3591. Min Range: -6.3591
Max Act: 5.9216. Min Act: -0.1700
Data Index: 2083618 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3591. Min Range: -6.3591
Max Act: 5.8904. Min Act: -0.1700
Data Index: 750057 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19