Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1024 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1423. Min Range: -5.1423
Max Act: 5.1423. Min Act: -0.1700
Data Index: 297597 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.9860. Min Act: -0.1700
Data Index: 6161938 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.9547. Min Act: -0.1700
Data Index: 3796231 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.9235. Min Act: -0.1700
Data Index: 2345366 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.8922. Min Act: -0.1700
Data Index: 3813839 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.8922. Min Act: -0.1700
Data Index: 4843082 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.8610. Min Act: -0.1700
Data Index: 2345367 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.8297. Min Act: -0.1700
Data Index: 470048 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7985. Min Act: -0.1700
Data Index: 5628400 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7985. Min Act: -0.1700
Data Index: 5892577 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7985. Min Act: -0.1700
Data Index: 3176303 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7672. Min Act: -0.1700
Data Index: 2764500 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7672. Min Act: -0.1700
Data Index: 422540 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7672. Min Act: -0.1700
Data Index: 190342 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7672. Min Act: -0.1700
Data Index: 1873812 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7672. Min Act: -0.1700
Data Index: 1054400 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7672. Min Act: -0.1700
Data Index: 4127124 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7360. Min Act: -0.1700
Data Index: 5442973 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7047. Min Act: -0.1700
Data Index: 2345365 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1423. Min Range: -5.1423
Max Act: 4.7047. Min Act: -0.1700
Data Index: 4382473 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19