Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5864. Min Range: -6.5864
Max Act: 6.5864. Min Act: -0.1700
Data Index: 6651281 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5864. Min Range: -6.5864
Max Act: 6.2427. Min Act: -0.1700
Data Index: 7913200 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5864. Min Range: -6.5864
Max Act: 6.1802. Min Act: -0.1700
Data Index: 1698402 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5864. Min Range: -6.5864
Max Act: 6.0552. Min Act: -0.1700
Data Index: 160139 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5864. Min Range: -6.5864
Max Act: 6.0239. Min Act: -0.1700
Data Index: 2589937 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.9927. Min Act: -0.1700
Data Index: 5452798 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5864. Min Range: -6.5864
Max Act: 6.0239. Min Act: -0.1700
Data Index: 2292481 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.9302. Min Act: -0.1700
Data Index: 7545060 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.9614. Min Act: -0.1700
Data Index: 1323650 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5864. Min Range: -6.5864
Max Act: 6.0239. Min Act: -0.1700
Data Index: 2292709 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.9927. Min Act: -0.1700
Data Index: 6386187 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.9302. Min Act: -0.1700
Data Index: 2307097 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.9927. Min Act: -0.1700
Data Index: 6386190 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.9614. Min Act: -0.1700
Data Index: 650674 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.9302. Min Act: -0.1700
Data Index: 5504458 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.9302. Min Act: -0.1700
Data Index: 5452795 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.8989. Min Act: -0.1700
Data Index: 1323647 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.8989. Min Act: -0.1700
Data Index: 1288341 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.8364. Min Act: -0.1700
Data Index: 4821744 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5864. Min Range: -6.5864
Max Act: 5.9302. Min Act: -0.1700
Data Index: 8081222 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19