Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2876 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.7498. Min Act: -0.1700
Data Index: 6191357 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.2185. Min Act: -0.1700
Data Index: 5078085 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.1873. Min Act: -0.1700
Data Index: 7730730 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7498. Min Range: -6.7498
Max Act: 6.0310. Min Act: -0.1700
Data Index: 2949334 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.9373. Min Act: -0.1700
Data Index: 1980420 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.9060. Min Act: -0.1700
Data Index: 6115764 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.9060. Min Act: -0.1700
Data Index: 697255 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.9060. Min Act: -0.1700
Data Index: 4694358 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.9060. Min Act: -0.1700
Data Index: 6585506 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.8748. Min Act: -0.1700
Data Index: 6191369 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.8435. Min Act: -0.1700
Data Index: 6191363 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.8123. Min Act: -0.1699
Data Index: 530982 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.7810. Min Act: -0.1700
Data Index: 8426040 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.7810. Min Act: -0.1700
Data Index: 4451647 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.7810. Min Act: -0.1700
Data Index: 6954198 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.7810. Min Act: -0.1700
Data Index: 6585505 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.7498. Min Act: -0.1700
Data Index: 7478364 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.7498. Min Act: -0.1700
Data Index: 2817279 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.7498. Min Act: -0.1700
Data Index: 5471312 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7498. Min Range: -6.7498
Max Act: 5.7498. Min Act: -0.1700
Data Index: 2281965 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19