Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4364 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0709. Min Range: -4.0709
Max Act: 4.0709. Min Act: -0.1700
Data Index: 2976898 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0709. Min Range: -4.0709
Max Act: 4.0553. Min Act: -0.1700
Data Index: 67231 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.8521. Min Act: -0.1700
Data Index: 1312969 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.8052. Min Act: -0.1700
Data Index: 3984051 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.7896. Min Act: -0.1700
Data Index: 687922 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.7896. Min Act: -0.1700
Data Index: 3426341 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.7739. Min Act: -0.1700
Data Index: 7402985 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.7739. Min Act: -0.1700
Data Index: 8799789 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.7583. Min Act: -0.1700
Data Index: 67230 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.7114. Min Act: -0.1700
Data Index: 6136702 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.7114. Min Act: -0.1700
Data Index: 7348630 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.6957. Min Act: -0.1700
Data Index: 3125809 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.6957. Min Act: -0.1700
Data Index: 6857232 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.6957. Min Act: -0.1700
Data Index: 4695367 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.6801. Min Act: -0.1700
Data Index: 5950519 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.6801. Min Act: -0.1700
Data Index: 457282 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.6957. Min Act: -0.1700
Data Index: 8002074 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.6801. Min Act: -0.1700
Data Index: 7370210 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.6644. Min Act: -0.1700
Data Index: 828725 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0709. Min Range: -4.0709
Max Act: 3.6488. Min Act: -0.1700
Data Index: 8748350 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19