Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.9075. Min Act: -0.1700
Data Index: 4235596 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.8762. Min Act: -0.1700
Data Index: 4313567 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.8450. Min Act: -0.1700
Data Index: 8744791 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7825. Min Act: -0.1700
Data Index: 6593429 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7512. Min Act: -0.1700
Data Index: 1350445 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7825. Min Act: -0.1700
Data Index: 1945785 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7200. Min Act: -0.1700
Data Index: 2274861 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7825. Min Act: -0.1700
Data Index: 1959450 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7512. Min Act: -0.1700
Data Index: 7338605 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7200. Min Act: -0.1700
Data Index: 6876651 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7200. Min Act: -0.1700
Data Index: 6737540 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.7200. Min Act: -0.1700
Data Index: 8631266 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6575. Min Act: -0.1700
Data Index: 7476321 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6887. Min Act: -0.1700
Data Index: 1014431 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6887. Min Act: -0.1700
Data Index: 7802418 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6887. Min Act: -0.1700
Data Index: 2417852 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6575. Min Act: -0.1700
Data Index: 221060 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6575. Min Act: -0.1700
Data Index: 5510351 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.6887. Min Act: -0.1700
Data Index: 2204925 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9075. Min Range: -4.9075
Max Act: 4.5950. Min Act: -0.1700
Data Index: 8413497 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19