Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.7846. Min Act: -0.1700
Data Index: 5131669 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.6596. Min Act: -0.1700
Data Index: 8709155 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.6596. Min Act: -0.1700
Data Index: 2202589 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.5971. Min Act: -0.1700
Data Index: 1003194 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.5033. Min Act: -0.1700
Data Index: 2449865 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.5346. Min Act: -0.1700
Data Index: 2887410 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.4408. Min Act: -0.1700
Data Index: 7292603 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.4096. Min Act: -0.1700
Data Index: 7555896 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.3471. Min Act: -0.1700
Data Index: 5385865 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.3471. Min Act: -0.1700
Data Index: 1771970 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.3471. Min Act: -0.1700
Data Index: 2632 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.2221. Min Act: -0.1700
Data Index: 5536036 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.2533. Min Act: -0.1700
Data Index: 3220069 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.2221. Min Act: -0.1700
Data Index: 5733348 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.2221. Min Act: -0.1700
Data Index: 1021169 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.1908. Min Act: -0.1700
Data Index: 6194881 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.1596. Min Act: -0.1700
Data Index: 4902159 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.1596. Min Act: -0.1700
Data Index: 8561317 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.1596. Min Act: -0.1700
Data Index: 6568855 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7846. Min Range: -7.7846
Max Act: 7.1283. Min Act: -0.1700
Data Index: 7655991 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19