Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1079. Min Range: -3.1079
Max Act: 3.1079. Min Act: -0.1700
Data Index: 3371998 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1079. Min Range: -3.1079
Max Act: 3.0606. Min Act: -0.1700
Data Index: 6797755 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9500. Min Act: -0.1700
Data Index: 3930869 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9658. Min Act: -0.1700
Data Index: 7825193 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9500. Min Act: -0.1700
Data Index: 7775447 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9342. Min Act: -0.1700
Data Index: 7765449 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9658. Min Act: -0.1700
Data Index: 6007085 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9500. Min Act: -0.1700
Data Index: 6376306 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9816. Min Act: -0.1700
Data Index: 1761230 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9342. Min Act: -0.1700
Data Index: 1690689 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9183. Min Act: -0.1700
Data Index: 5088506 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9183. Min Act: -0.1700
Data Index: 2118373 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9342. Min Act: -0.1700
Data Index: 6713519 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.8866. Min Act: -0.1700
Data Index: 3637888 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.8866. Min Act: -0.1700
Data Index: 4557652 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9025. Min Act: -0.1700
Data Index: 6571305 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.8866. Min Act: -0.1700
Data Index: 3286462 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.9025. Min Act: -0.1700
Data Index: 4683836 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.8707. Min Act: -0.1700
Data Index: 151726 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1079. Min Range: -3.1079
Max Act: 2.8707. Min Act: -0.1700
Data Index: 6070352 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19