Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 647 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.4888. Min Act: -0.1700
Data Index: 8028002 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.3013. Min Act: -0.1700
Data Index: 7345084 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.2388. Min Act: -0.1700
Data Index: 642225 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.2388. Min Act: -0.1700
Data Index: 8497159 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.2388. Min Act: -0.1700
Data Index: 8003948 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.1450. Min Act: -0.1700
Data Index: 3219180 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.1138. Min Act: -0.1700
Data Index: 1579131 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.1138. Min Act: -0.1700
Data Index: 3922421 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.1450. Min Act: -0.1700
Data Index: 5523142 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.0513. Min Act: -0.1700
Data Index: 6585157 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.0513. Min Act: -0.1700
Data Index: 6787668 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.0513. Min Act: -0.1700
Data Index: 2609707 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.0513. Min Act: -0.1700
Data Index: 3015014 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.0200. Min Act: -0.1700
Data Index: 1077987 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4888. Min Range: -6.4888
Max Act: 5.9888. Min Act: -0.1700
Data Index: 1658110 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4888. Min Range: -6.4888
Max Act: 5.9575. Min Act: -0.1700
Data Index: 6581321 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4888. Min Range: -6.4888
Max Act: 5.9888. Min Act: -0.1700
Data Index: 4589210 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4888. Min Range: -6.4888
Max Act: 5.9888. Min Act: -0.1700
Data Index: 8831996 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4888. Min Range: -6.4888
Max Act: 5.9888. Min Act: -0.1700
Data Index: 870978 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4888. Min Range: -6.4888
Max Act: 6.0200. Min Act: -0.1700
Data Index: 1957962 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19