Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.9816. Min Act: -0.1700
Data Index: 8406461 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.9503. Min Act: -0.1700
Data Index: 4325823 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.9503. Min Act: -0.1700
Data Index: 1553738 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.9191. Min Act: -0.1700
Data Index: 2709113 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.9191. Min Act: -0.1700
Data Index: 5545178 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.8096. Min Act: -0.1700
Data Index: 4339338 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.7940. Min Act: -0.1700
Data Index: 3514716 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.7627. Min Act: -0.1700
Data Index: 7080778 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.7940. Min Act: -0.1700
Data Index: 6563778 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.7627. Min Act: -0.1700
Data Index: 5196814 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.7471. Min Act: -0.1700
Data Index: 190340 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.7314. Min Act: -0.1700
Data Index: 5196813 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.7158. Min Act: -0.1700
Data Index: 107203 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.7158. Min Act: -0.1700
Data Index: 5788148 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.6845. Min Act: -0.1700
Data Index: 8817890 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.6688. Min Act: -0.1700
Data Index: 4889427 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.6532. Min Act: -0.1700
Data Index: 8261893 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.6688. Min Act: -0.1700
Data Index: 1086678 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.6845. Min Act: -0.1700
Data Index: 7253691 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9816. Min Range: -3.9816
Max Act: 3.6532. Min Act: -0.1700
Data Index: 3719921 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19