Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3060 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.2124. Min Act: -0.1700
Data Index: 2495846 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.1186. Min Act: -0.1700
Data Index: 2344933 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.0561. Min Act: -0.1700
Data Index: 972372 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.0561. Min Act: -0.1700
Data Index: 4197728 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.0249. Min Act: -0.1700
Data Index: 827552 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.9624. Min Act: -0.1700
Data Index: 777253 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.8686. Min Act: -0.1700
Data Index: 2680466 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.8061. Min Act: -0.1700
Data Index: 8652117 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.8061. Min Act: -0.1700
Data Index: 7505176 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.7749. Min Act: -0.1700
Data Index: 5562667 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.7124. Min Act: -0.1700
Data Index: 1509328 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.7124. Min Act: -0.1700
Data Index: 8122147 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.6811. Min Act: -0.1700
Data Index: 1690729 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.6811. Min Act: -0.1700
Data Index: 3555300 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.6811. Min Act: -0.1700
Data Index: 8505111 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.6811. Min Act: -0.1700
Data Index: 553085 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.6811. Min Act: -0.1700
Data Index: 7800275 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.6499. Min Act: -0.1700
Data Index: 1682215 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.5874. Min Act: -0.1700
Data Index: 935204 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.5874. Min Act: -0.1700
Data Index: 1186464 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19