Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6233 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.6308. Min Act: -0.1700
Data Index: 4766722 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.5995. Min Act: -0.1700
Data Index: 8394423 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.5058. Min Act: -0.1700
Data Index: 5669577 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.4745. Min Act: -0.1700
Data Index: 8067512 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.4433. Min Act: -0.1700
Data Index: 1498866 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.4745. Min Act: -0.1700
Data Index: 420964 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.4120. Min Act: -0.1700
Data Index: 4713560 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.4120. Min Act: -0.1700
Data Index: 7279704 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.3808. Min Act: -0.1700
Data Index: 8286117 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.4120. Min Act: -0.1700
Data Index: 6636951 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.3808. Min Act: -0.1700
Data Index: 8168271 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.3495. Min Act: -0.1700
Data Index: 1473182 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.3808. Min Act: -0.1700
Data Index: 579482 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.3808. Min Act: -0.1700
Data Index: 5862237 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.3495. Min Act: -0.1700
Data Index: 2274198 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.3495. Min Act: -0.1700
Data Index: 3020297 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.3495. Min Act: -0.1700
Data Index: 8165691 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.2870. Min Act: -0.1700
Data Index: 7217432 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.3183. Min Act: -0.1700
Data Index: 1834208 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6308. Min Range: -4.6308
Max Act: 4.3183. Min Act: -0.1700
Data Index: 882338 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19