Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4017 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5627. Min Range: -4.5627
Max Act: 4.5627. Min Act: -0.1700
Data Index: 4121650 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5627. Min Range: -4.5627
Max Act: 4.4377. Min Act: -0.1700
Data Index: 4121651 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5627. Min Range: -4.5627
Max Act: 4.2189. Min Act: -0.1700
Data Index: 7035079 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5627. Min Range: -4.5627
Max Act: 4.1876. Min Act: -0.1700
Data Index: 6902870 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5627. Min Range: -4.5627
Max Act: 4.1564. Min Act: -0.1700
Data Index: 3658744 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5627. Min Range: -4.5627
Max Act: 4.0626. Min Act: -0.1700
Data Index: 6558614 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5627. Min Range: -4.5627
Max Act: 4.0626. Min Act: -0.1700
Data Index: 6753979 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5627. Min Range: -4.5627
Max Act: 4.0626. Min Act: -0.1700
Data Index: 3961244 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5627. Min Range: -4.5627
Max Act: 4.0001. Min Act: -0.1700
Data Index: 822686 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5627. Min Range: -4.5627
Max Act: 4.0001. Min Act: -0.1700
Data Index: 8604461 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5627. Min Range: -4.5627
Max Act: 4.0001. Min Act: -0.1700
Data Index: 7035077 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5627. Min Range: -4.5627
Max Act: 3.9688. Min Act: -0.1700
Data Index: 4744457 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5627. Min Range: -4.5627
Max Act: 3.9376. Min Act: -0.1700
Data Index: 1676473 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5627. Min Range: -4.5627
Max Act: 3.9376. Min Act: -0.1700
Data Index: 8207887 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5627. Min Range: -4.5627
Max Act: 3.9376. Min Act: -0.1700
Data Index: 5550355 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5627. Min Range: -4.5627
Max Act: 3.9063. Min Act: -0.1700
Data Index: 5527232 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5627. Min Range: -4.5627
Max Act: 3.9063. Min Act: -0.1700
Data Index: 3177146 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5627. Min Range: -4.5627
Max Act: 3.8438. Min Act: -0.1700
Data Index: 76921 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5627. Min Range: -4.5627
Max Act: 3.8750. Min Act: -0.1700
Data Index: 1036932 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5627. Min Range: -4.5627
Max Act: 3.8750. Min Act: -0.1700
Data Index: 6549960 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19