Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 809 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1541. Min Range: -4.1541
Max Act: 4.1541. Min Act: -0.1700
Data Index: 4034470 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1541. Min Range: -4.1541
Max Act: 4.1541. Min Act: -0.1700
Data Index: 6395178 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1541. Min Range: -4.1541
Max Act: 4.1228. Min Act: -0.1700
Data Index: 8639951 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1541. Min Range: -4.1541
Max Act: 4.0603. Min Act: -0.1700
Data Index: 4997509 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1541. Min Range: -4.1541
Max Act: 4.0916. Min Act: -0.1700
Data Index: 8358953 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1541. Min Range: -4.1541
Max Act: 4.0603. Min Act: -0.1700
Data Index: 6472372 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1541. Min Range: -4.1541
Max Act: 4.0603. Min Act: -0.1700
Data Index: 6104089 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1541. Min Range: -4.1541
Max Act: 4.0290. Min Act: -0.1700
Data Index: 5222040 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1541. Min Range: -4.1541
Max Act: 4.0290. Min Act: -0.1700
Data Index: 3171706 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1541. Min Range: -4.1541
Max Act: 4.0290. Min Act: -0.1700
Data Index: 5977865 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1541. Min Range: -4.1541
Max Act: 3.9978. Min Act: -0.1700
Data Index: 152893 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1541. Min Range: -4.1541
Max Act: 3.9665. Min Act: -0.1700
Data Index: 4069312 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1541. Min Range: -4.1541
Max Act: 3.9978. Min Act: -0.1700
Data Index: 5507101 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1541. Min Range: -4.1541
Max Act: 3.9665. Min Act: -0.1700
Data Index: 4036345 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1541. Min Range: -4.1541
Max Act: 3.9665. Min Act: -0.1700
Data Index: 6168682 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1541. Min Range: -4.1541
Max Act: 3.9353. Min Act: -0.1700
Data Index: 5867148 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1541. Min Range: -4.1541
Max Act: 3.9353. Min Act: -0.1700
Data Index: 7298379 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1541. Min Range: -4.1541
Max Act: 3.9353. Min Act: -0.1700
Data Index: 7945391 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1541. Min Range: -4.1541
Max Act: 3.9353. Min Act: -0.1700
Data Index: 7610261 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1541. Min Range: -4.1541
Max Act: 3.9353. Min Act: -0.1700
Data Index: 7348272 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19