Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1946 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3615. Min Range: -6.3615
Max Act: 6.3615. Min Act: -0.1700
Data Index: 156852 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3615. Min Range: -6.3615
Max Act: 6.0803. Min Act: -0.1700
Data Index: 7632766 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3615. Min Range: -6.3615
Max Act: 6.0178. Min Act: -0.1700
Data Index: 8487304 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.9865. Min Act: -0.1700
Data Index: 1698497 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.9240. Min Act: -0.1700
Data Index: 8071153 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.8928. Min Act: -0.1700
Data Index: 4323676 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.8928. Min Act: -0.1700
Data Index: 829994 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.8303. Min Act: -0.1700
Data Index: 3253556 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.8303. Min Act: -0.1700
Data Index: 219143 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.7990. Min Act: -0.1700
Data Index: 6422132 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.8303. Min Act: -0.1700
Data Index: 1688772 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.7990. Min Act: -0.1700
Data Index: 4561497 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.7990. Min Act: -0.1700
Data Index: 616155 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.7990. Min Act: -0.1700
Data Index: 7802390 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.7678. Min Act: -0.1700
Data Index: 2431617 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.7365. Min Act: -0.1700
Data Index: 8008351 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.7365. Min Act: -0.1700
Data Index: 2575220 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.7053. Min Act: -0.1700
Data Index: 6741267 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.7053. Min Act: -0.1700
Data Index: 633837 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3615. Min Range: -6.3615
Max Act: 5.7053. Min Act: -0.1700
Data Index: 4977882 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19