Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3667 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.9138. Min Act: -0.1700
Data Index: 5680159 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.8201. Min Act: -0.1700
Data Index: 3141476 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.8201. Min Act: -0.1700
Data Index: 5178549 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.7888. Min Act: -0.1700
Data Index: 5163260 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.7576. Min Act: -0.1700
Data Index: 4454962 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.6951. Min Act: -0.1700
Data Index: 714584 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.6951. Min Act: -0.1700
Data Index: 1230734 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.6951. Min Act: -0.1700
Data Index: 2347560 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.6638. Min Act: -0.1699
Data Index: 2534747 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.6638. Min Act: -0.1700
Data Index: 6385640 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.6326. Min Act: -0.1700
Data Index: 4863298 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.6638. Min Act: -0.1700
Data Index: 6357042 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.6013. Min Act: -0.1700
Data Index: 7456844 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.5701. Min Act: -0.1700
Data Index: 2437933 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.5701. Min Act: -0.1700
Data Index: 6317485 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.6013. Min Act: -0.1700
Data Index: 3422558 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.6326. Min Act: -0.1700
Data Index: 2761018 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.5701. Min Act: -0.1699
Data Index: 4910136 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.5701. Min Act: -0.1700
Data Index: 298786 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9138. Min Range: -4.9138
Max Act: 4.5701. Min Act: -0.1700
Data Index: 7604970 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19