Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4062 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.9825. Min Act: -0.1700
Data Index: 3848682 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.9513. Min Act: -0.1700
Data Index: 5640219 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.9513. Min Act: -0.1700
Data Index: 7719668 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.9200. Min Act: -0.1700
Data Index: 1821609 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.7950. Min Act: -0.1700
Data Index: 7498874 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.7950. Min Act: -0.1700
Data Index: 6137679 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.7638. Min Act: -0.1700
Data Index: 2574225 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.7638. Min Act: -0.1700
Data Index: 3888608 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.7325. Min Act: -0.1700
Data Index: 7255840 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.7013. Min Act: -0.1700
Data Index: 7834051 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.7013. Min Act: -0.1700
Data Index: 6558427 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.7013. Min Act: -0.1700
Data Index: 3080183 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.7013. Min Act: -0.1700
Data Index: 6159444 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.6700. Min Act: -0.1700
Data Index: 4594853 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.7013. Min Act: -0.1700
Data Index: 7130066 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.7013. Min Act: -0.1700
Data Index: 5703435 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.6700. Min Act: -0.1700
Data Index: 5296976 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.6700. Min Act: -0.1700
Data Index: 1976105 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.6700. Min Act: -0.1700
Data Index: 3438039 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9825. Min Range: -4.9825
Max Act: 4.6700. Min Act: -0.1700
Data Index: 3805217 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19