Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.3510. Min Act: -0.1700
Data Index: 8314931 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.2573. Min Act: -0.1700
Data Index: 695490 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.2573. Min Act: -0.1700
Data Index: 4008651 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.2573. Min Act: -0.1700
Data Index: 4542161 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.2260. Min Act: -0.1700
Data Index: 2599932 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.2260. Min Act: -0.1700
Data Index: 7104665 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.2260. Min Act: -0.1700
Data Index: 5701783 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1948. Min Act: -0.1700
Data Index: 184134 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1948. Min Act: -0.1700
Data Index: 7175843 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1948. Min Act: -0.1656
Data Index: 2700735 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1948. Min Act: -0.1700
Data Index: 5883210 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1635. Min Act: -0.1700
Data Index: 4058806 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1635. Min Act: -0.1700
Data Index: 4688146 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1635. Min Act: -0.1700
Data Index: 2451342 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1635. Min Act: -0.1700
Data Index: 4277023 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1635. Min Act: -0.1700
Data Index: 5103963 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1323. Min Act: -0.1700
Data Index: 2780643 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1010. Min Act: -0.1699
Data Index: 69966 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1010. Min Act: -0.1700
Data Index: 3521848 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3510. Min Range: -4.3510
Max Act: 4.1323. Min Act: -0.1700
Data Index: 7050829 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19