Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3667 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0318. Min Range: -5.0318
Max Act: 5.0006. Min Act: -0.1700
Data Index: 6017057 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0318. Min Range: -5.0318
Max Act: 5.0318. Min Act: -0.1700
Data Index: 6357046 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.9693. Min Act: -0.1700
Data Index: 7677402 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.8756. Min Act: -0.1700
Data Index: 92219 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.8756. Min Act: -0.1700
Data Index: 3599753 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.8443. Min Act: -0.1700
Data Index: 4670997 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.8131. Min Act: -0.1700
Data Index: 1445090 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.7818. Min Act: -0.1700
Data Index: 2507183 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.7506. Min Act: -0.1700
Data Index: 3270337 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.7818. Min Act: -0.1700
Data Index: 1994478 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.6881. Min Act: -0.1700
Data Index: 2076855 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.7193. Min Act: -0.1700
Data Index: 1449218 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.7193. Min Act: -0.1700
Data Index: 2336565 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.7193. Min Act: -0.1700
Data Index: 1497519 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.7193. Min Act: -0.1700
Data Index: 6980850 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.7193. Min Act: -0.1700
Data Index: 5410121 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.6881. Min Act: -0.1700
Data Index: 4719751 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.6881. Min Act: -0.1700
Data Index: 6582036 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.6881. Min Act: -0.1700
Data Index: 6901174 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0318. Min Range: -5.0318
Max Act: 4.6568. Min Act: -0.1700
Data Index: 5193027 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19