Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1541 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6341. Min Range: -8.6341
Max Act: 8.6341. Min Act: -0.1700
Data Index: 8487261 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.6966. Min Act: -0.1700
Data Index: 7286359 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.6341. Min Act: -0.1700
Data Index: 2078100 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.6341. Min Act: -0.1700
Data Index: 6800617 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.5091. Min Act: -0.1700
Data Index: 1941730 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.5091. Min Act: -0.1700
Data Index: 6722217 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.5091. Min Act: -0.1700
Data Index: 2076455 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.5091. Min Act: -0.1700
Data Index: 5939814 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.4154. Min Act: -0.1700
Data Index: 8385531 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.3841. Min Act: -0.1700
Data Index: 1991082 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.3841. Min Act: -0.1700
Data Index: 1215821 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.3529. Min Act: -0.1700
Data Index: 379639 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.3216. Min Act: -0.1700
Data Index: 4938202 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.2591. Min Act: -0.1700
Data Index: 1053793 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.2279. Min Act: -0.1700
Data Index: 5586942 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.1966. Min Act: -0.1700
Data Index: 5032535 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.2279. Min Act: -0.1700
Data Index: 7600521 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.1966. Min Act: -0.1700
Data Index: 4569831 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.2279. Min Act: -0.1700
Data Index: 4857835 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6341. Min Range: -8.6341
Max Act: 7.1966. Min Act: -0.1700
Data Index: 5626183 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19