Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1487. Min Range: -6.1487
Max Act: 6.1487. Min Act: -0.1700
Data Index: 7087799 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1487. Min Range: -6.1487
Max Act: 6.1175. Min Act: -0.1700
Data Index: 53681 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1487. Min Range: -6.1487
Max Act: 6.0237. Min Act: -0.1700
Data Index: 8646198 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1487. Min Range: -6.1487
Max Act: 6.0237. Min Act: -0.1700
Data Index: 8646197 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.9925. Min Act: -0.1700
Data Index: 4660588 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.9612. Min Act: -0.1700
Data Index: 4129492 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.9612. Min Act: -0.1700
Data Index: 1628606 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8987. Min Act: -0.1700
Data Index: 4419272 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.9300. Min Act: -0.1700
Data Index: 8065260 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8987. Min Act: -0.1700
Data Index: 2102597 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8987. Min Act: -0.1700
Data Index: 1785858 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8987. Min Act: -0.1700
Data Index: 4757933 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8987. Min Act: -0.1700
Data Index: 1563447 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8675. Min Act: -0.1700
Data Index: 3427019 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8987. Min Act: -0.1700
Data Index: 7760080 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8675. Min Act: -0.1700
Data Index: 6482028 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8050. Min Act: -0.1700
Data Index: 2374343 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8362. Min Act: -0.1700
Data Index: 3285487 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8050. Min Act: -0.1700
Data Index: 4180337 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1487. Min Range: -6.1487
Max Act: 5.8362. Min Act: -0.1700
Data Index: 1264555 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19