Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.7712. Min Act: -0.1700
Data Index: 8222588 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.7868. Min Act: -0.1700
Data Index: 8158851 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.7556. Min Act: -0.1700
Data Index: 104688 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.7243. Min Act: -0.1700
Data Index: 7247239 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.7086. Min Act: -0.1700
Data Index: 6631518 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.6930. Min Act: -0.1700
Data Index: 8168637 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.6930. Min Act: -0.1700
Data Index: 4293466 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.6617. Min Act: -0.1700
Data Index: 5667182 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.6304. Min Act: -0.1700
Data Index: 112762 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.5991. Min Act: -0.1700
Data Index: 1715460 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.5678. Min Act: -0.1700
Data Index: 8358578 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.5678. Min Act: -0.1700
Data Index: 6753089 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.5678. Min Act: -0.1700
Data Index: 1307762 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.5521. Min Act: -0.1700
Data Index: 6817412 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.5208. Min Act: -0.1700
Data Index: 1685676 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.5365. Min Act: -0.1700
Data Index: 3779437 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.5365. Min Act: -0.1700
Data Index: 7417022 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.5208. Min Act: -0.1700
Data Index: 8500720 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.5208. Min Act: -0.1700
Data Index: 3550001 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7868. Min Range: -3.7868
Max Act: 3.5052. Min Act: -0.1700
Data Index: 4016354 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19