Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2154 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1815. Min Range: -3.1815
Max Act: 3.1657. Min Act: -0.1700
Data Index: 6945598 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1815. Min Range: -3.1815
Max Act: 3.1815. Min Act: -0.1700
Data Index: 1209555 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1815. Min Range: -3.1815
Max Act: 3.0396. Min Act: -0.1700
Data Index: 2706487 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1815. Min Range: -3.1815
Max Act: 3.0081. Min Act: -0.1700
Data Index: 3328024 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.9922. Min Act: -0.1700
Data Index: 5187792 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.9764. Min Act: -0.1700
Data Index: 375142 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.9922. Min Act: -0.1700
Data Index: 2393463 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.9606. Min Act: -0.1700
Data Index: 3358283 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.9606. Min Act: -0.1700
Data Index: 722279 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.9131. Min Act: -0.1700
Data Index: 7788002 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.8972. Min Act: -0.1700
Data Index: 8468040 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.9131. Min Act: -0.1700
Data Index: 8333724 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.8655. Min Act: -0.1700
Data Index: 7508063 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.8814. Min Act: -0.1700
Data Index: 6906251 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.8814. Min Act: -0.1700
Data Index: 7296072 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.8814. Min Act: -0.1700
Data Index: 6245388 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.8496. Min Act: -0.1700
Data Index: 4350285 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.8655. Min Act: -0.1700
Data Index: 4424107 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.8496. Min Act: -0.1700
Data Index: 1627036 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1815. Min Range: -3.1815
Max Act: 2.8496. Min Act: -0.1700
Data Index: 3600524 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19