Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1597 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1005. Min Range: -3.1005
Max Act: 3.1005. Min Act: -0.1700
Data Index: 3360443 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1005. Min Range: -3.1005
Max Act: 3.0689. Min Act: -0.1700
Data Index: 6327787 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1005. Min Range: -3.1005
Max Act: 3.0689. Min Act: -0.1700
Data Index: 7855651 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1005. Min Range: -3.1005
Max Act: 3.0216. Min Act: -0.1700
Data Index: 8439730 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1005. Min Range: -3.1005
Max Act: 3.0058. Min Act: -0.1700
Data Index: 6142709 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.9900. Min Act: -0.1700
Data Index: 540059 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.9900. Min Act: -0.1700
Data Index: 6308910 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.9742. Min Act: -0.1700
Data Index: 6411868 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.9742. Min Act: -0.1700
Data Index: 8679446 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.9425. Min Act: -0.1700
Data Index: 6722987 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.9425. Min Act: -0.1700
Data Index: 5502002 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.9267. Min Act: -0.1700
Data Index: 5647621 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.9267. Min Act: -0.1700
Data Index: 2627214 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.9108. Min Act: -0.1700
Data Index: 1738223 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.9108. Min Act: -0.1700
Data Index: 5647616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.9108. Min Act: -0.1700
Data Index: 3652587 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.8950. Min Act: -0.1700
Data Index: 747784 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.8950. Min Act: -0.1700
Data Index: 4568355 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.8791. Min Act: -0.1700
Data Index: 7843716 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1005. Min Range: -3.1005
Max Act: 2.8474. Min Act: -0.1700
Data Index: 4679150 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19