Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1297 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5903. Min Range: -7.5903
Max Act: 7.5903. Min Act: -0.1700
Data Index: 1547336 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5903. Min Range: -7.5903
Max Act: 7.3090. Min Act: -0.1700
Data Index: 250489 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5903. Min Range: -7.5903
Max Act: 7.1215. Min Act: -0.1700
Data Index: 6193994 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5903. Min Range: -7.5903
Max Act: 7.0903. Min Act: -0.1700
Data Index: 267933 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5903. Min Range: -7.5903
Max Act: 7.0590. Min Act: -0.1700
Data Index: 2207241 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5903. Min Range: -7.5903
Max Act: 7.1215. Min Act: -0.1700
Data Index: 3376373 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5903. Min Range: -7.5903
Max Act: 7.0590. Min Act: -0.1700
Data Index: 2421182 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.9965. Min Act: -0.1700
Data Index: 6521465 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.9965. Min Act: -0.1700
Data Index: 4422303 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.9965. Min Act: -0.1700
Data Index: 3320103 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.9965. Min Act: -0.1700
Data Index: 5342588 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.9340. Min Act: -0.1700
Data Index: 3051555 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.9028. Min Act: -0.1700
Data Index: 2568388 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.9028. Min Act: -0.1700
Data Index: 2284356 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.9028. Min Act: -0.1700
Data Index: 1377642 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.8715. Min Act: -0.1700
Data Index: 7729327 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.8715. Min Act: -0.1700
Data Index: 1289231 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.8403. Min Act: -0.1700
Data Index: 5235040 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.8715. Min Act: -0.1700
Data Index: 339664 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5903. Min Range: -7.5903
Max Act: 6.8715. Min Act: -0.1700
Data Index: 6070271 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19