Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5423 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.5983. Min Act: -0.1700
Data Index: 1238757 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.4421. Min Act: -0.1700
Data Index: 6961884 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.2546. Min Act: -0.1700
Data Index: 8529192 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.0671. Min Act: -0.1700
Data Index: 8324644 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.0671. Min Act: -0.1700
Data Index: 4202018 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.0671. Min Act: -0.1700
Data Index: 4170824 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.0671. Min Act: -0.1700
Data Index: 8203020 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.0671. Min Act: -0.1700
Data Index: 3945946 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.0358. Min Act: -0.1700
Data Index: 7363137 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5983. Min Range: -6.5983
Max Act: 5.9733. Min Act: -0.1700
Data Index: 4708324 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5983. Min Range: -6.5983
Max Act: 5.9733. Min Act: -0.1700
Data Index: 1613975 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5983. Min Range: -6.5983
Max Act: 5.9421. Min Act: -0.1700
Data Index: 1459993 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5983. Min Range: -6.5983
Max Act: 5.9108. Min Act: -0.1700
Data Index: 2162078 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5983. Min Range: -6.5983
Max Act: 5.9108. Min Act: -0.1700
Data Index: 5080913 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5983. Min Range: -6.5983
Max Act: 5.9108. Min Act: -0.1700
Data Index: 4903371 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5983. Min Range: -6.5983
Max Act: 5.9108. Min Act: -0.1700
Data Index: 5673895 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5983. Min Range: -6.5983
Max Act: 5.9421. Min Act: -0.1700
Data Index: 5222774 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5983. Min Range: -6.5983
Max Act: 5.8796. Min Act: -0.1700
Data Index: 113043 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5983. Min Range: -6.5983
Max Act: 5.8796. Min Act: -0.1700
Data Index: 5097586 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5983. Min Range: -6.5983
Max Act: 5.8796. Min Act: -0.1700
Data Index: 708882 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19