Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5096 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.8882. Min Act: -0.1700
Data Index: 2156596 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.8569. Min Act: -0.1700
Data Index: 2144775 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.8882. Min Act: -0.1700
Data Index: 7339779 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.8257. Min Act: -0.1700
Data Index: 2462023 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.8257. Min Act: -0.1700
Data Index: 2913267 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.8257. Min Act: -0.1700
Data Index: 3950979 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7944. Min Act: -0.1700
Data Index: 455680 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7944. Min Act: -0.1700
Data Index: 1127978 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7632. Min Act: -0.1700
Data Index: 4026464 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7632. Min Act: -0.1700
Data Index: 1254512 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7632. Min Act: -0.1700
Data Index: 3303014 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 7767423 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7319. Min Act: -0.1700
Data Index: 2212834 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 7785807 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 1365019 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.6694. Min Act: -0.1700
Data Index: 1908386 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 1689442 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 8382774 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 355248 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.6382. Min Act: -0.1700
Data Index: 7659539 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19