Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1477 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1255. Min Range: -6.1255
Max Act: 6.1255. Min Act: -0.1700
Data Index: 3849902 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1255. Min Range: -6.1255
Max Act: 6.0005. Min Act: -0.1700
Data Index: 1209430 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.8442. Min Act: -0.1700
Data Index: 7201943 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.8755. Min Act: -0.1700
Data Index: 5549363 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.7817. Min Act: -0.1700
Data Index: 3700333 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.5630. Min Act: -0.1700
Data Index: 5655364 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.3755. Min Act: -0.1700
Data Index: 928697 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.4380. Min Act: -0.1700
Data Index: 6024895 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.3755. Min Act: -0.1700
Data Index: 3240876 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.3755. Min Act: -0.1700
Data Index: 7337628 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.2817. Min Act: -0.1700
Data Index: 4234107 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.2505. Min Act: -0.1700
Data Index: 8085186 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.0630. Min Act: -0.1700
Data Index: 7199499 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.1255. Min Act: -0.1700
Data Index: 5441558 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.0317. Min Act: -0.1700
Data Index: 6283722 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.0630. Min Act: -0.1700
Data Index: 5170389 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.0630. Min Act: -0.1700
Data Index: 5134392 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.0630. Min Act: -0.1700
Data Index: 3133656 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1255. Min Range: -6.1255
Max Act: 4.9692. Min Act: -0.1700
Data Index: 3360420 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1255. Min Range: -6.1255
Max Act: 5.0630. Min Act: -0.1700
Data Index: 5844104 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19