Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5474 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7482. Min Range: -7.7482
Max Act: 7.7482. Min Act: -0.1700
Data Index: 5983430 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7482. Min Range: -7.7482
Max Act: 7.3732. Min Act: -0.1700
Data Index: 5391429 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7482. Min Range: -7.7482
Max Act: 7.3107. Min Act: -0.1700
Data Index: 2139014 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7482. Min Range: -7.7482
Max Act: 7.2170. Min Act: -0.1700
Data Index: 39244 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7482. Min Range: -7.7482
Max Act: 7.1545. Min Act: -0.1700
Data Index: 2695711 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7482. Min Range: -7.7482
Max Act: 7.1232. Min Act: -0.1700
Data Index: 6174296 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7482. Min Range: -7.7482
Max Act: 7.0607. Min Act: -0.1700
Data Index: 5643474 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.9982. Min Act: -0.1700
Data Index: 5479983 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.9670. Min Act: -0.1700
Data Index: 4482497 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.9357. Min Act: -0.1700
Data Index: 6842699 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.9045. Min Act: -0.1700
Data Index: 7948581 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.8732. Min Act: -0.1700
Data Index: 1679392 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.8732. Min Act: -0.1700
Data Index: 8543591 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.8732. Min Act: -0.1700
Data Index: 361411 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.8732. Min Act: -0.1700
Data Index: 8742191 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.8107. Min Act: -0.1700
Data Index: 4199100 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.8420. Min Act: -0.1700
Data Index: 1203311 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.8420. Min Act: -0.1700
Data Index: 1102377 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.8420. Min Act: -0.1700
Data Index: 1612091 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7482. Min Range: -7.7482
Max Act: 6.8420. Min Act: -0.1700
Data Index: 7979386 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19