Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4670 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.8377. Min Act: -0.1700
Data Index: 3833144 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.6502. Min Act: -0.1700
Data Index: 3307486 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.3065. Min Act: -0.1700
Data Index: 2562176 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.2752. Min Act: -0.1700
Data Index: 2824775 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.2440. Min Act: -0.1700
Data Index: 5083310 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.2440. Min Act: -0.1700
Data Index: 8684404 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.2440. Min Act: -0.1700
Data Index: 5146404 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.1502. Min Act: -0.1700
Data Index: 5818230 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.1502. Min Act: -0.1700
Data Index: 3558453 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.1190. Min Act: -0.1700
Data Index: 4960356 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.0877. Min Act: -0.1700
Data Index: 2932327 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.0565. Min Act: -0.1700
Data Index: 1252474 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.0565. Min Act: -0.1700
Data Index: 1885453 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.0565. Min Act: -0.1700
Data Index: 2947116 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8377. Min Range: -7.8377
Max Act: 6.9940. Min Act: -0.1700
Data Index: 433212 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8377. Min Range: -7.8377
Max Act: 7.0252. Min Act: -0.1700
Data Index: 3406387 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8377. Min Range: -7.8377
Max Act: 6.9940. Min Act: -0.1700
Data Index: 3578498 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8377. Min Range: -7.8377
Max Act: 6.9940. Min Act: -0.1700
Data Index: 1224621 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8377. Min Range: -7.8377
Max Act: 6.9627. Min Act: -0.1700
Data Index: 7685177 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8377. Min Range: -7.8377
Max Act: 6.9627. Min Act: -0.1700
Data Index: 2779864 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19