Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.4489. Min Act: -0.1700
Data Index: 8609374 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.3551. Min Act: -0.1700
Data Index: 4266783 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.3551. Min Act: -0.1700
Data Index: 3484294 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1989. Min Act: -0.1700
Data Index: 1457896 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.0739. Min Act: -0.1700
Data Index: 1086014 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.0114. Min Act: -0.1700
Data Index: 8109346 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.9489. Min Act: -0.1700
Data Index: 8609375 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.9489. Min Act: -0.1700
Data Index: 6016531 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.9489. Min Act: -0.1700
Data Index: 8240772 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.9489. Min Act: -0.1700
Data Index: 6621335 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.9176. Min Act: -0.1700
Data Index: 4698567 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.9176. Min Act: -0.1700
Data Index: 7068545 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.9176. Min Act: -0.1700
Data Index: 129017 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.9176. Min Act: -0.1700
Data Index: 7647195 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.9176. Min Act: -0.1700
Data Index: 5932572 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.8864. Min Act: -0.1700
Data Index: 5383392 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.8864. Min Act: -0.1700
Data Index: 5786340 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.8239. Min Act: -0.1700
Data Index: 2750367 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.8864. Min Act: -0.1700
Data Index: 4552662 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4489. Min Range: -6.4489
Max Act: 5.8551. Min Act: -0.1700
Data Index: 2864684 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19