Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.4350. Min Act: -0.1700
Data Index: 4807352 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.3725. Min Act: -0.1700
Data Index: 5801472 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.3725. Min Act: -0.1700
Data Index: 3412384 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.3725. Min Act: -0.1700
Data Index: 1154249 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.3413. Min Act: -0.1700
Data Index: 2968316 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.3100. Min Act: -0.1700
Data Index: 519949 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2788. Min Act: -0.1700
Data Index: 3957359 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2163. Min Act: -0.1700
Data Index: 3797686 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2475. Min Act: -0.1700
Data Index: 5997382 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2163. Min Act: -0.1700
Data Index: 4565326 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2163. Min Act: -0.1700
Data Index: 6680184 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2163. Min Act: -0.1700
Data Index: 6088226 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1850. Min Act: -0.1700
Data Index: 3352471 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1850. Min Act: -0.1700
Data Index: 1973074 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1850. Min Act: -0.1700
Data Index: 3487394 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2163. Min Act: -0.1700
Data Index: 718086 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2163. Min Act: -0.1700
Data Index: 5364613 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1850. Min Act: -0.1700
Data Index: 5682843 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1850. Min Act: -0.1700
Data Index: 4921804 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1537. Min Act: -0.1700
Data Index: 5734611 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19