Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2685 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4207. Min Range: -6.4207
Max Act: 6.4207. Min Act: -0.1700
Data Index: 1620489 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4207. Min Range: -6.4207
Max Act: 6.3582. Min Act: -0.1700
Data Index: 3835839 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4207. Min Range: -6.4207
Max Act: 6.1082. Min Act: -0.1700
Data Index: 3550521 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4207. Min Range: -6.4207
Max Act: 6.1082. Min Act: -0.1700
Data Index: 168215 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4207. Min Range: -6.4207
Max Act: 6.1082. Min Act: -0.1700
Data Index: 5089429 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4207. Min Range: -6.4207
Max Act: 6.0770. Min Act: -0.1700
Data Index: 1071432 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4207. Min Range: -6.4207
Max Act: 6.0457. Min Act: -0.1700
Data Index: 3358295 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4207. Min Range: -6.4207
Max Act: 6.0145. Min Act: -0.1700
Data Index: 2451968 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.9832. Min Act: -0.1700
Data Index: 54567 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.9832. Min Act: -0.1700
Data Index: 186878 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.9832. Min Act: -0.1700
Data Index: 8148309 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.9520. Min Act: -0.1700
Data Index: 8758943 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.9207. Min Act: -0.1700
Data Index: 7818719 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.9207. Min Act: -0.1700
Data Index: 430503 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.9207. Min Act: -0.1700
Data Index: 5172316 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.8895. Min Act: -0.1700
Data Index: 257847 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.8895. Min Act: -0.1700
Data Index: 5707917 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.8895. Min Act: -0.1700
Data Index: 7269616 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.8895. Min Act: -0.1700
Data Index: 2114881 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4207. Min Range: -6.4207
Max Act: 5.8895. Min Act: -0.1700
Data Index: 2392013 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19