Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 630 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2408. Min Range: -9.2408
Max Act: 9.2408. Min Act: -0.1700
Data Index: 241832 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2408. Min Range: -9.2408
Max Act: 8.1783. Min Act: -0.1700
Data Index: 8425076 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.9908. Min Act: -0.1700
Data Index: 2206612 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.8658. Min Act: -0.1700
Data Index: 4846641 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.9283. Min Act: -0.1700
Data Index: 307997 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.8033. Min Act: -0.1700
Data Index: 8655386 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.8033. Min Act: -0.1700
Data Index: 2850262 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.7408. Min Act: -0.1700
Data Index: 91855 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.8033. Min Act: -0.1700
Data Index: 7027321 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.7095. Min Act: -0.1700
Data Index: 8392785 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.7408. Min Act: -0.1700
Data Index: 1201842 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.7095. Min Act: -0.1700
Data Index: 6263806 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.6783. Min Act: -0.1700
Data Index: 3436645 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.6783. Min Act: -0.1700
Data Index: 2237819 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.6470. Min Act: -0.1700
Data Index: 8013437 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.6783. Min Act: -0.1700
Data Index: 2654685 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.6158. Min Act: -0.1700
Data Index: 2992803 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.6158. Min Act: -0.1700
Data Index: 1284921 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.5845. Min Act: -0.1700
Data Index: 7849638 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2408. Min Range: -9.2408
Max Act: 7.5845. Min Act: -0.1700
Data Index: 7826014 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19