Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.5944. Min Act: -0.1700
Data Index: 5697754 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.2819. Min Act: -0.1700
Data Index: 4725561 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.1569. Min Act: -0.1700
Data Index: 7513303 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0944. Min Act: -0.1700
Data Index: 7970523 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0944. Min Act: -0.1700
Data Index: 422822 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0944. Min Act: -0.1700
Data Index: 1871841 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0632. Min Act: -0.1700
Data Index: 6415519 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0632. Min Act: -0.1700
Data Index: 7224993 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0632. Min Act: -0.1700
Data Index: 1014264 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0319. Min Act: -0.1700
Data Index: 2303341 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0319. Min Act: -0.1700
Data Index: 158310 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0007. Min Act: -0.1700
Data Index: 3926514 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0007. Min Act: -0.1700
Data Index: 5212744 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0007. Min Act: -0.1700
Data Index: 4595651 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0007. Min Act: -0.1700
Data Index: 404232 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0007. Min Act: -0.1700
Data Index: 1250585 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5944. Min Range: -6.5944
Max Act: 6.0007. Min Act: -0.1700
Data Index: 690314 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5944. Min Range: -6.5944
Max Act: 5.9694. Min Act: -0.1700
Data Index: 5308750 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5944. Min Range: -6.5944
Max Act: 5.9382. Min Act: -0.1700
Data Index: 6158381 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5944. Min Range: -6.5944
Max Act: 5.9694. Min Act: -0.1700
Data Index: 4813750 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19