Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1828 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.4947. Min Act: -0.1700
Data Index: 1208670 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.4010. Min Act: -0.1700
Data Index: 3186054 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.2447. Min Act: -0.1700
Data Index: 1958817 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.2447. Min Act: -0.1700
Data Index: 1051551 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.1822. Min Act: -0.1700
Data Index: 1958818 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.2135. Min Act: -0.1700
Data Index: 3496561 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.2135. Min Act: -0.1700
Data Index: 3056767 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.1822. Min Act: -0.1700
Data Index: 8571967 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.2135. Min Act: -0.1700
Data Index: 7784907 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.1197. Min Act: -0.1700
Data Index: 6002904 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.0885. Min Act: -0.1700
Data Index: 2703838 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.0885. Min Act: -0.1700
Data Index: 2379126 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.0260. Min Act: -0.1700
Data Index: 1034128 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.0885. Min Act: -0.1700
Data Index: 3818893 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.0885. Min Act: -0.1700
Data Index: 4474705 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.0572. Min Act: -0.1700
Data Index: 4100838 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.0572. Min Act: -0.1700
Data Index: 6266387 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.0260. Min Act: -0.1700
Data Index: 7710836 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4947. Min Range: -5.4947
Max Act: 4.9947. Min Act: -0.1700
Data Index: 7743553 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4947. Min Range: -5.4947
Max Act: 5.0260. Min Act: -0.1700
Data Index: 674702 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19