Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5823 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3615. Min Range: -8.3615
Max Act: 8.3615. Min Act: -0.1700
Data Index: 5054593 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3615. Min Range: -8.3615
Max Act: 8.2990. Min Act: -0.1700
Data Index: 4560184 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3615. Min Range: -8.3615
Max Act: 8.2990. Min Act: -0.1700
Data Index: 15280 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3615. Min Range: -8.3615
Max Act: 8.1740. Min Act: -0.1700
Data Index: 2216536 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3615. Min Range: -8.3615
Max Act: 8.1740. Min Act: -0.1700
Data Index: 3243890 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3615. Min Range: -8.3615
Max Act: 8.1115. Min Act: -0.1700
Data Index: 1315497 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3615. Min Range: -8.3615
Max Act: 8.1740. Min Act: -0.1700
Data Index: 6214950 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3615. Min Range: -8.3615
Max Act: 8.0490. Min Act: -0.1700
Data Index: 228152 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.9865. Min Act: -0.1700
Data Index: 7975224 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.9240. Min Act: -0.1700
Data Index: 6654310 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.9240. Min Act: -0.1700
Data Index: 7146294 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.8615. Min Act: -0.1700
Data Index: 2794805 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.8615. Min Act: -0.1700
Data Index: 5865408 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.8615. Min Act: -0.1700
Data Index: 5478638 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.8615. Min Act: -0.1700
Data Index: 7687641 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.7990. Min Act: -0.1700
Data Index: 6579635 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.7990. Min Act: -0.1700
Data Index: 4641992 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.7990. Min Act: -0.1700
Data Index: 6117521 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.7990. Min Act: -0.1700
Data Index: 5317317 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3615. Min Range: -8.3615
Max Act: 7.7678. Min Act: -0.1700
Data Index: 6559286 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19