Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 616 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1586. Min Range: -6.1586
Max Act: 6.1586. Min Act: -0.1700
Data Index: 3153660 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1586. Min Range: -6.1586
Max Act: 6.0961. Min Act: -0.1700
Data Index: 8528204 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1586. Min Range: -6.1586
Max Act: 6.0023. Min Act: -0.1700
Data Index: 7970651 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1586. Min Range: -6.1586
Max Act: 6.0023. Min Act: -0.1700
Data Index: 6415943 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.9086. Min Act: -0.1700
Data Index: 7457026 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.9398. Min Act: -0.1700
Data Index: 7765773 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.9398. Min Act: -0.1700
Data Index: 3930752 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.9398. Min Act: -0.1700
Data Index: 8447836 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.8461. Min Act: -0.1700
Data Index: 5157038 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.8461. Min Act: -0.1700
Data Index: 6999475 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.8148. Min Act: -0.1700
Data Index: 350626 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.8461. Min Act: -0.1700
Data Index: 1646901 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.8461. Min Act: -0.1700
Data Index: 5700022 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.8148. Min Act: -0.1700
Data Index: 4858463 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.8461. Min Act: -0.1700
Data Index: 5680184 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.8461. Min Act: -0.1700
Data Index: 2624823 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.7836. Min Act: -0.1700
Data Index: 1691932 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.7836. Min Act: -0.1700
Data Index: 2932945 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.7836. Min Act: -0.1700
Data Index: 4080590 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1586. Min Range: -6.1586
Max Act: 5.7523. Min Act: -0.1700
Data Index: 5109539 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19