Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4138 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.5167. Min Act: -0.1700
Data Index: 3293580 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.4542. Min Act: -0.1700
Data Index: 5445891 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.4542. Min Act: -0.1700
Data Index: 7358469 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.3605. Min Act: -0.1700
Data Index: 1771634 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.2667. Min Act: -0.1700
Data Index: 2644324 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.2667. Min Act: -0.1700
Data Index: 3276092 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.2667. Min Act: -0.1700
Data Index: 1445639 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.2355. Min Act: -0.1700
Data Index: 8546372 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.2355. Min Act: -0.1700
Data Index: 1168384 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.2355. Min Act: -0.1700
Data Index: 1835715 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.2042. Min Act: -0.1700
Data Index: 6623824 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.2042. Min Act: -0.1700
Data Index: 386368 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.2042. Min Act: -0.1700
Data Index: 6771874 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.1730. Min Act: -0.1700
Data Index: 3483370 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.1730. Min Act: -0.1700
Data Index: 4901019 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.1417. Min Act: -0.1700
Data Index: 3005633 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.1105. Min Act: -0.1700
Data Index: 5076462 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.1417. Min Act: -0.1700
Data Index: 8745631 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.1730. Min Act: -0.1700
Data Index: 7114740 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5167. Min Range: -4.5167
Max Act: 4.1105. Min Act: -0.1700
Data Index: 4276745 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19