Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.3535. Min Act: -0.1700
Data Index: 4146871 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.3221. Min Act: -0.1700
Data Index: 1980932 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.3378. Min Act: -0.1700
Data Index: 1854572 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.2750. Min Act: -0.1700
Data Index: 3022652 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.2436. Min Act: -0.1700
Data Index: 6269519 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.2436. Min Act: -0.1700
Data Index: 2967194 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1964. Min Act: -0.1700
Data Index: 4689165 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1964. Min Act: -0.1700
Data Index: 4938738 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1807. Min Act: -0.1700
Data Index: 7671334 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1492. Min Act: -0.1700
Data Index: 5929729 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1492. Min Act: -0.1700
Data Index: 1342984 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1177. Min Act: -0.1700
Data Index: 1980931 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1335. Min Act: -0.1700
Data Index: 649243 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1177. Min Act: -0.1700
Data Index: 3253204 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1020. Min Act: -0.1700
Data Index: 2784134 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.0862. Min Act: -0.1700
Data Index: 6122752 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1177. Min Act: -0.1700
Data Index: 2929654 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1020. Min Act: -0.1700
Data Index: 6431553 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.1020. Min Act: -0.1700
Data Index: 2449237 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3535. Min Range: -3.3535
Max Act: 3.0704. Min Act: -0.1700
Data Index: 2369416 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19