Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3797 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.5091. Min Act: -0.1700
Data Index: 2729969 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.4778. Min Act: -0.1700
Data Index: 2506372 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.4153. Min Act: -0.1700
Data Index: 1394038 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.3841. Min Act: -0.1700
Data Index: 5445571 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.3216. Min Act: -0.1700
Data Index: 2113944 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.2903. Min Act: -0.1700
Data Index: 2385376 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.2903. Min Act: -0.1700
Data Index: 5319884 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.2591. Min Act: -0.1700
Data Index: 1716675 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.2591. Min Act: -0.1700
Data Index: 5534170 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.2591. Min Act: -0.1700
Data Index: 4664484 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.2278. Min Act: -0.1700
Data Index: 8235712 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.2278. Min Act: -0.1700
Data Index: 3485518 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.2278. Min Act: -0.1700
Data Index: 77972 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.1966. Min Act: -0.1700
Data Index: 5534155 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.2278. Min Act: -0.1700
Data Index: 4981239 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.2278. Min Act: -0.1700
Data Index: 4695410 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.1653. Min Act: -0.1700
Data Index: 6095953 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.1341. Min Act: -0.1700
Data Index: 4716824 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.1028. Min Act: -0.1700
Data Index: 3993677 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5091. Min Range: -5.5091
Max Act: 5.1028. Min Act: -0.1700
Data Index: 5040133 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19