Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.3811. Min Act: -0.1700
Data Index: 702236 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.3811. Min Act: -0.1700
Data Index: 6097626 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.3499. Min Act: -0.1700
Data Index: 1207613 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.3499. Min Act: -0.1700
Data Index: 3450707 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.2561. Min Act: -0.1700
Data Index: 2760878 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.2874. Min Act: -0.1700
Data Index: 5628018 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.2561. Min Act: -0.1700
Data Index: 3138162 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.2249. Min Act: -0.1700
Data Index: 6443172 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.1936. Min Act: -0.1700
Data Index: 8802016 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.2249. Min Act: -0.1700
Data Index: 911567 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.1936. Min Act: -0.1700
Data Index: 2760877 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.1624. Min Act: -0.1700
Data Index: 321832 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.2249. Min Act: -0.1700
Data Index: 5250547 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.1624. Min Act: -0.1700
Data Index: 5125159 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.1624. Min Act: -0.1700
Data Index: 2048170 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.1624. Min Act: -0.1700
Data Index: 5554604 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.1624. Min Act: -0.1700
Data Index: 702237 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.1624. Min Act: -0.1700
Data Index: 4945668 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.1624. Min Act: -0.1700
Data Index: 2462852 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3811. Min Range: -5.3811
Max Act: 5.1311. Min Act: -0.1700
Data Index: 329911 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19