Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2377 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.5168. Min Act: -0.1512
Data Index: 3491851 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.5168. Min Act: -0.1676
Data Index: 6789157 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.5080. Min Act: -0.1688
Data Index: 423620 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.5168. Min Act: -0.1688
Data Index: 8522687 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4553. Min Act: -0.1699
Data Index: 8421284 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4465. Min Act: -0.1378
Data Index: 5628032 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4289. Min Act: -0.1648
Data Index: 5044398 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4377. Min Act: -0.1700
Data Index: 4631032 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4377. Min Act: -0.1668
Data Index: 4424152 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4289. Min Act: -0.1494
Data Index: 3732791 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4113. Min Act: -0.1629
Data Index: 8499410 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4025. Min Act: -0.1608
Data Index: 6198371 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4025. Min Act: -0.1676
Data Index: 2469249 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4113. Min Act: -0.1591
Data Index: 7387925 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4113. Min Act: -0.1615
Data Index: 7611216 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4113. Min Act: -0.1688
Data Index: 68606 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.4025. Min Act: -0.1633
Data Index: 1179552 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.3937. Min Act: -0.1506
Data Index: 1767710 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.3937. Min Act: -0.1645
Data Index: 7234387 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5168. Min Range: -1.5168
Max Act: 1.3849. Min Act: -0.1408
Data Index: 8082290 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19