Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.9155. Min Act: -0.1700
Data Index: 930559 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.8529. Min Act: -0.1700
Data Index: 4612704 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.8529. Min Act: -0.1700
Data Index: 1079414 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.7904. Min Act: -0.1700
Data Index: 8615232 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.7591. Min Act: -0.1700
Data Index: 6493612 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.7278. Min Act: -0.1700
Data Index: 6493599 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.7278. Min Act: -0.1700
Data Index: 3439928 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.7278. Min Act: -0.1700
Data Index: 1874857 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6965. Min Act: -0.1700
Data Index: 3988093 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6965. Min Act: -0.1700
Data Index: 6248338 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6965. Min Act: -0.1700
Data Index: 8643686 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6965. Min Act: -0.1700
Data Index: 5854448 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6653. Min Act: -0.1700
Data Index: 652081 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6496. Min Act: -0.1700
Data Index: 990450 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6496. Min Act: -0.1700
Data Index: 3069347 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6340. Min Act: -0.1700
Data Index: 5662157 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6653. Min Act: -0.1700
Data Index: 4930411 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6496. Min Act: -0.1700
Data Index: 930560 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6653. Min Act: -0.1700
Data Index: 6097073 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9155. Min Range: -3.9155
Max Act: 3.6653. Min Act: -0.1700
Data Index: 6248363 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19