Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 616 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.3578. Min Act: -0.1700
Data Index: 6204221 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.3578. Min Act: -0.1700
Data Index: 7389529 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.3265. Min Act: -0.1700
Data Index: 1286680 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.3265. Min Act: -0.1700
Data Index: 6216767 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.2640. Min Act: -0.1700
Data Index: 3677496 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.1703. Min Act: -0.1700
Data Index: 3985491 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.1078. Min Act: -0.1700
Data Index: 3677497 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.0453. Min Act: -0.1700
Data Index: 3064805 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.0140. Min Act: -0.1700
Data Index: 4091081 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3578. Min Range: -6.3578
Max Act: 6.0140. Min Act: -0.1700
Data Index: 1934771 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.9828. Min Act: -0.1700
Data Index: 2913673 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.9515. Min Act: -0.1700
Data Index: 8614388 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.9203. Min Act: -0.1700
Data Index: 4184471 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.9203. Min Act: -0.1700
Data Index: 7783633 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.9203. Min Act: -0.1700
Data Index: 8524067 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.8890. Min Act: -0.1700
Data Index: 5809223 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.8890. Min Act: -0.1700
Data Index: 2647789 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.8578. Min Act: -0.1700
Data Index: 7781493 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.8890. Min Act: -0.1700
Data Index: 6623521 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3578. Min Range: -6.3578
Max Act: 5.8890. Min Act: -0.1700
Data Index: 6824270 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19