Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.4646. Min Act: -0.1700
Data Index: 4482918 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.3708. Min Act: -0.1700
Data Index: 2945488 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.4021. Min Act: -0.1700
Data Index: 4671787 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.4021. Min Act: -0.1700
Data Index: 5049253 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.3396. Min Act: -0.1700
Data Index: 7769270 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.3083. Min Act: -0.1700
Data Index: 8039105 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.3083. Min Act: -0.1700
Data Index: 1952232 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1833. Min Act: -0.1700
Data Index: 1581933 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2146. Min Act: -0.1700
Data Index: 602637 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2146. Min Act: -0.1700
Data Index: 1964623 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1833. Min Act: -0.1700
Data Index: 4388281 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1833. Min Act: -0.1700
Data Index: 4913794 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1833. Min Act: -0.1700
Data Index: 5803509 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1208. Min Act: -0.1700
Data Index: 1220325 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1521. Min Act: -0.1700
Data Index: 6369081 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1521. Min Act: -0.1700
Data Index: 6639363 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.0896. Min Act: -0.1700
Data Index: 7317483 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1208. Min Act: -0.1700
Data Index: 5237512 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1208. Min Act: -0.1700
Data Index: 3922660 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.0896. Min Act: -0.1700
Data Index: 5660951 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19